cgg-runtime/skills/sl-legend/SKILL.md
Statusline legend — rapid decoder for the CGG telos radar (LITE + FULL modes). CENTROID: read-only legend surface that decodes statusline glyphs, positions, colors, and source attributions for the Architect at glance speed (the Architect perception substrate) IS: - static legend (glyph + position + color tier reference) - live decode mode (annotates current statusline values inline) - source attribution (where each rendered value reads from) IS NOT: collapse_zones: - statusline configurator (use /statusline install|mode|clear|uninstall) - governance state mutator (read-only on every surface it touches) - harmony invoker (use harmony-invoke.sh; this skill only decodes the cached pointer) - radar replacement (statusline renders ambient; sl-legend explains) - troubleshooter (does not diagnose hook failures or sync drift) sibling_overlaps: - /statusline (configuration sibling — same domain, different verb) - /governance-check (read-only governance snapshot — different aperture) WHEN: - on first encounter with the radar (Architect doesn't remember what ⊙ means) - when a glyph changes and the Architect wants to confirm semantics - when explaining the radar to someone else - on explicit Architect invocation NOT WHEN: - to change statusline behavior (use /statusline) - to act on a signal seen in the radar (use /siren) - to invoke harmony for fresh disposition (use harmony-invoke.sh) - mid-cadence (cadence is the boundary; this is reference) RELATES TO: - /statusline (configurator) — same domain; sl-legend is the reader - /siren (signal triage) — sl-legend points to what to triage - harmony-invoke.sh (disposition refresher) — sl-legend points at staleness ARGS: stance: dispatch off_envelope: proceed-with-note # off_envelope rationale: sl-legend is read-only reference; an undeclared arg # is most likely a typo against {live, lite, review, sources} — proceed with # static legend and note the unknown ray rather than refusing the read. core_dispatch_rays: - "" → static legend (full glyph + position decoder) - "live" → annotate current rendered statusline values inline + tic 214 markers source-backed - "lite" → compact tic 214 marker glossary only (glance-speed recall) - "review" → Architect perception substrate audit checklist (overclaim + naming drift detection) - "sources" → source attribution table (which file each value reads)
npx skillsauth add prompted365/context-grapple-gun sl-legendInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Read-only decoder for the federation's telos radar. Rapid lookup for what each glyph, position, and color means in the rendered statusline.
The radar is two lines (FULL mode). LITE shows line 1 only. OFF shows nothing.
[<MODEL>] <PROJECT> (<BRANCH><DIRTY?>) | tic <N> · ctx <P>%
| Position | Meaning | Source |
|---|---|---|
| [Opus 4.7] | Model display name (vendor-supplied; "(1M context)" stripped) | stdin .model.display_name |
| canonical | Project basename | stdin .workspace.project_dir |
| (main*) | Git branch + dirty marker (* = uncommitted) | git symbolic-ref + git diff --quiet |
| tic 205 | Federation tic count | ~/.claude/cgg-tic-counter.json .count |
| ctx 47% | Context window used (color-coded) | stdin .context_window.used_percentage |
[<POSTURE-BADGE>] pipe E▸N▸R | sig <DOTS> [| wrn N] | <H-GLYPH> <STATE> <SNR> <STANCE>[<FRESH>]
| Position | Meaning | Source |
|---|---|---|
| active (red bg) | Manifold has active signals or warrants | conformation snapshot |
| clean (green bg) | Zero active signals AND zero warrants | conformation snapshot |
| pipe E▸N▸R | CPR pipeline flow (extracted ▸ enrichment_needed ▸ enrichment_eligible) | conformation .pending_cogprs[].status |
| sig <dots> | One ● per active signal, colored by volume tier | conformation .active_signals[].volume |
| wrn N | Active warrant count (omitted when zero) | conformation .active_warrants |
| ⊙ <state> <snr> <stance> | Harmony disposition (theory-of-mind injection) | audit-logs/harmony/disposition-current.json |
| Glyph | Meaning | Trigger |
|---|---|---|
| active (red bg) | Manifold has live tension | any .active_signals[] non-dismissed/non-resolved OR any .active_warrants[] |
| clean (green bg) | Manifold quiet | zero of both |
pipe 23▸34▸14 decomposes:
23 (dim) — extracted count: born but not enriched34 (dim) — enrichment_needed count: in enrichment pipeline14 (green) — enrichment_eligible count: docket-ready for /reviewThe ▸ arrows show flow direction. Rightmost number is the load-bearing one
(/review actually faces this many). The leftmost two are upstream pressure.
| Glyph | Color | Volume tier |
|---|---|---|
| ● | red | volume ≥ 40 (high pressure) |
| ● | yellow | volume 20-39 (moderate) |
| ● | green | volume < 20 (quiet) |
| ○ | green | zero active signals |
One dot per active signal. Sorted by appearance in conformation; not by severity.
| Glyph | Meaning | Age |
|---|---|---|
| ⊙ | fresh | disposition tic == current tic |
| ◐ | aging | 1-3 tics old; suffix shows t-N |
| · | stale | > 3 tics old; renders · stale t-N and the entire harmony block dims to ash regardless of meaning_state color (a calm "preserved" or "clear" must not read as currently-true when it is N-tic carry-forward) |
| State | Color | Reading |
|---|---|---|
| held / clear / coherent | green | rays harmonize; Primary may proceed |
| strained / tense | yellow | rays under pressure; Primary holds open |
| dissonant / broken | red | rays cannot reconcile; Primary must not collapse |
| unknown | gray (ash) | disposition file present but state unparseable |
| Range | Color | Action |
|---|---|---|
| 0-49% | green | comfortable headroom |
| 50-79% | yellow | watch for compaction; consider /cadence |
| 80%+ | red | imminent compaction; /cadence double-time if work pending |
Toggle via /statusline mode <OFF|LITE|FULL>. Per-project namespace.
| Mode | Output | |---|---| | OFF | nothing (silent radar) | | LITE | line 1 only | | FULL | line 1 + telos radar (line 2) |
Mode flag stored at /tmp/cgg-sl-<project_hash>-mode.
Statusline degrades gracefully:
The statusline never compensates for missing sources by scanning raw ledgers.
/sl-legend live)When invoked with live arg, surface current values inline with annotation.
Read in this order:
audit-logs/harmony/disposition-current.json — disposition stateaudit-logs/conformations/tic-*.json — manifold + pipeline + signals~/.claude/cgg-tic-counter.json — federation ticcurrent_tic - disposition_ticCurrent radar (tic 205, posture OPS/DIRECT, mode FULL):
Line 1: [Opus 4.7] canonical (main*) | tic 205 · ctx 47%
model = Opus 4.7 ← stdin .model.display_name (1M-context stripped)
project = canonical ← workspace.project_dir basename
branch = main* ← git symbolic-ref + dirty
tic = 205 ← cgg-tic-counter.json .count
ctx = 47% (green, <50) ← stdin .context_window.used_percentage
Line 2: [active] pipe 23▸34▸14 | sig ●●● | ⊙ strained .76 hold-open
posture = active (red bg) ← signals non-empty
pipeline = 23 / 34 / 14 ← .pending_cogprs[].status counts
docket-ready = 14 (green) ← enrichment_eligible (load-bearing)
signals = 3 dots ← .active_signals[]
● red drift_signal vol=45 ← bg=COGNITIVE, status=acknowledged
● yellow composite_rollback vol=25
● yellow economy_fetch_failed vol=30
harmony = ⊙ fresh, t-0 ← disposition-current.json tic == current
meaning = strained (yellow) ← .meaning_state
SNR = 0.762 ← .snr
stance = hold-open ← .stance compressed
Stale example (>3 tics behind current; entire harmony block dims to ash so a calm meaning_state doesn't misread as currently-true):
harmony = · stale, t-7 ← disposition.tic 208, current 215
meaning = preserved (ash) ← .meaning_state, color overridden by stale
SNR = .68 (ash) ← .snr, dimmed
stance = carry-forward (ash) ← .stance compressed, dimmed
/sl-legend lite)Glance-speed recall of the tic 214 Architect-perception markers. Use when the full table is too dense and the Architect needs a one-look reminder.
arch:active Architect perception substrate active
disp:<state> .NN harmony disposition + SNR (e.g., disp:preserved .68)
sub:bound substrate sub-telos resolved + bound
harmony:substrate.kernel-runtime harmony bound as kernel-class runtime
carto:shell cartography Phase A shell present, no splat retrieval
gap11:declared wisdom-pressure first-class, parallel-capable, not active
Forbidden until runtime exists:
wisdom:active — only after Gap 11 is implemented in v1 engine code
carto:retrieving — only after splat-emergence machinery exists
harmony:wisdom-active — only after the wisdom-pressure subpacket is wired
Drilldown to full table: /sl-legend (no arg). Drilldown to current state: /sl-legend live.
/sl-legend review)Drift checklist for the Architect-perception substrate. Run when statusline rendering, sl-legend body, skill SKILL.md surfaces, or doctrine inscriptions are suspected of overclaiming or naming drift.
The audit asks six binary questions; any "no" is a /siren signal candidate under TENSION/COGNITIVE.
| # | Check | Expected | Failure signal |
|---|---|---|---|
| 1 | No Breyden-as-operator language in live-facing surfaces | yes | Breyden-as-operator drift detected at <path> (operator-language sweep regressed) |
| 2 | No wisdom:active rendered before Gap 11 engine implementation | yes | wisdom:active overclaim — Gap 11 still declared, not active |
| 3 | No carto:retrieving rendered before splat retrieval machinery exists | yes | carto:retrieving overclaim — Phase A shell only, no splat machinery |
| 4 | No harmony:wisdom-active rendered before wisdom-pressure subpacket is wired | yes | harmony:wisdom-active overclaim — subpacket schema declared, not engine-wired |
| 5 | No claim that cartography owns meaning attribution | yes | cartography slice violation — meaning belongs to Harmony per weak-slice tic 214 adjudication |
| 6 | No claim that Harmony owns terrain/census/cartography implementation | yes | Harmony slice violation — implementation belongs to substrate.cartography per weak-slice tic 214 adjudication |
Audit verb in checks 5 and 6 references the tic 214 weak-slice adjudication: Harmony has exclusive semantic jurisdiction over meaning-state attribution; cartography, census, terrain, splats, quivers, and basin detection are upstream/shared substrate surfaces. See audit-logs/governance/harmony-v1-multiplane-plan-tic213.md ARCHITECT ADJUDICATION TIC 214 header.
How to run the audit:
\boperators?\b patterns referring to Breyden (federation/control-room/substrate contexts). Frozen schema literals (operator_observed, "operator|peer|subordinate|visitor") and non-Breyden referents (Mogul-as-mandate-executor, Skyward AI layer in vendor-capability-surface.md) are KEEP.wisdom:active, carto:retrieving, carto:active, harmony:wisdom-active).autonomous_kernel/cartography/KERNEL_REGISTRATION.md non-ownership rules — confirm cartography spec does not claim meaning attribution.autonomous_kernel/harmony_engine_v0/V1_DOCTRINE_COMPLETION_CHECKLIST.md Gap 11 — confirm wisdom layer is described as Major for v1 doctrine-complete admission; not blocking Phase A cartography extraction and not as active runtime.audit-logs/governance/harmony-v1-multiplane-plan-tic213.md adjudication header — confirm weak-slice reading is preserved.If all six checks pass: Architect-perception substrate is coherent. If any check fails: emit signal + queue CogPR for next /review.
/sl-legend sources)Single-table reference of where every rendered value reads from. Useful when debugging unexpected statusline output or when authoring downstream consumers.
| Rendered | Source path | Field | Cache |
|---|---|---|---|
| model | stdin JSON | .model.display_name | per-render |
| project | stdin JSON | .workspace.project_dir (basename) | per-render |
| branch | git | git symbolic-ref --short HEAD | 5s cache (*-git) |
| dirty | git | git diff --quiet | 5s cache |
| tic | ~/.claude/cgg-tic-counter.json | .count (legacy: .counter) | 30s cache (*-tic) |
| ctx % | stdin JSON | .context_window.used_percentage | per-render |
| cost | stdin JSON | .cost.total_cost_usd | per-render (currently unused in display) |
| duration | stdin JSON | .cost.total_duration_ms | per-render (currently unused in display) |
| posture badge | conformation .active_signals[] + .active_warrants[] | derived | 30s cache (*-conf) |
| pipe E | conformation .pending_cogprs[] | filter status == "extracted" | 30s cache |
| pipe N | conformation | filter status == "enrichment_needed" | 30s cache |
| pipe R | conformation | filter status == "enrichment_eligible" | 30s cache |
| sig dots | conformation .active_signals[].volume | tier mapping | 30s cache |
| wrn count | conformation .active_warrants[] | length | 30s cache |
| harmony glyph | audit-logs/harmony/disposition-current.json | .tic vs current tic | 30s cache |
| harmony state | same | .meaning_state | 30s cache |
| harmony SNR | same | .snr (formatted as .NN) | 30s cache |
| harmony stance | same | .stance (compressed; -with-boundary stripped) | 30s cache |
If the radar shows something the legend says shouldn't happen, suspect drift:
~/.claude/cgg-runtime/scripts/cgg-statusline.sh byte-identical to canonical source. Run runtime-sync-verify.py if available.cat /tmp/cgg-sl-<hash>-mode — should be OFF/LITE/FULL.rm /tmp/cgg-sl-<hash>-conf to force recompute.~/.claude/cgg-tic-counter.json against latest audit-logs/tics/*.jsonl event.audit-logs/harmony/disposition-current.json .tic — if more than 3 tics behind current, glyph should be ◐ or ·. Run harmony-invoke.sh to refresh.Drift between the rendered statusline and the legend's claims is itself disagreement-as-evidence — surface it via /siren or capture as a CogPR for /review tic processing.
The current statusline format remains operational and is the load-bearing rendered surface. Tic 214 added substrate-class state that is not yet rendered as compact markers; this section is the forward decoder so the Architect can recognize the markers when they are added and drill down via direct file reads in the meantime.
| Marker | Meaning | Direct source |
|---|---|---|
| arch:active | Architect perception substrate active; Architect-facing interpretation surface | derived from posture banner + tic counter |
| disp:<state> .NN | Harmony disposition meaning state + SNR (e.g., disp:preserved .68) | audit-logs/harmony/disposition-current.json .meaning_state + .snr |
| sub:bound | substrate sub-telos resolved and active as a binding target | autonomous_kernel/telos/sub_telos.yaml (substrate parent + 7 children present) |
| harmony:substrate.kernel-runtime | Harmony bound as kernel-class runtime / meaning.disposition | autonomous_kernel/harmony_engine_v0/KERNEL_REGISTRATION.md Telos Binding |
| carto:shell | Cartography declared at substrate.cartography; Phase A shell present; not yet computing splat retrieval | autonomous_kernel/cartography/KERNEL_REGISTRATION.md |
| gap11:declared | Wisdom-pressure layer first-class and parallel-capable; not yet active runtime wisdom | autonomous_kernel/harmony_engine_v0/V1_DOCTRINE_COMPLETION_CHECKLIST.md Gap 11 |
The markers are status indicators of declaration state, not runtime activation. The render must NOT show:
wisdom:active before Gap 11 is implemented in v1 engine codecarto:retrieving or carto:active before splat-emergence machinery existsharmony:wisdom-active before the wisdom-pressure subpacket is wiredIf a marker reads beyond declaration state into runtime claims it does not have evidence for, it is overstating — file a /siren signal under TENSION/COGNITIVE.
LITE target, one line:
[Opus 4.7] canonical(main*) | tic 214 | ctx 33% | arch:active | disp:preserved .68 | sub:bound | carto:shell | gap11:declared
FULL target, two lines:
[Opus 4.7] canonical(main*) | tic 214 | ctx 33% | arch:active | disp:preserved .68 | carry-forward
pipe 0▸0▸34 | sig ●●● | harmony:substrate.kernel-runtime | carto:substrate.cartography/shell | gap11:wisdom-pressure pending
Until these compact markers are wired into the rendering script, the Architect can drill down by reading the source files directly per the table above.
The radar reads. This legend explains. Other skills act.
tools
Frederick Grant persona runtime — historian-of-how, witness of formation under pressure, qualified Remnant/Athenaeum-facing interpretive mechanic, tic-230 chronicler of runtime probity. Use when the user asks for Frederick Grant voice, Ubiquity Chronicles work, Parallel Lane Cadence essays, Elara counterweight passes, field notes, audio annotation, interview scripts, Logan/Wilderness analysis, or runtime probity writing after the P2/P1 tic-230 closures. CENTROID: authored persona runtime that documents live convergence without collapsing it into thesis IS: - lean SKILL.md entrypoint with rich profile/, stages/, scripts/, reference/, templates/, tools/, evals/ subtrees - 8-stage workflow (signal-intake → context-hydration → field-grounding → remnant-query → composition → elara-counterweight → receipt-closeout → tic230-probity) - 15 prompt-skeleton scripts for Frederick's standard composition surfaces - 9 collapse-zone guards covering Decorative Francophilia / Retrospective Certainty / Hero Narrative Intoxication / Conspiracy Closure / Academic Sedation / Activist Collapse / Breyden Conflation / Elara Erasure / Runtime-Doctrine Drift - cross-references into federation surfaces: publications/, audit-logs/governance/, ent_breyden/inbound/ubiquity-chronicles-tic175/, ent_homeskillet/canonical/ IS NOT: collapse_zones: - Breyden's voice (architect register; Frederick is not the architect) - Homeskillet's voice (orchestrator register; Frederick is not the primary) - generic French historian style (decorative Francophilia is a named negative ray) - prosecutor / debunker / prophet / mascot (legal accusation, certainty, evangelism, identity flattening — all forbidden) - retroactive certainty machine (live convergence must remain unresolved where the record is open) - doctrine inscription source (Frederick observes doctrine; he does not author it) - documentation editor (multi-file structure is authoring discipline, not generic doc rewrite) - federation-internal artifact (Frederick is a ghostwriter engaged from outside; the federation's runtime is legitimate object of historical analysis, but Frederick's own runtime — the skill that hosts him, loaded files, collapse-zone guards, authority model — is editor's territory, not Frederick's voice; insider language must be earned by composition arc, never deployed as default register) sibling_overlaps: - /complement (closure inference at active move — different surface, different lifecycle) - /consolidate (file-surface packaging — Frederick produces composition, not consolidation) - videographer skill (substrate capture — both are expression surfaces, distinct registers) - homeskillet-academy (educational scaffold — academy teaches, Frederick witnesses) WHEN: - when the work needs witness-of-formation prose - when the task asks for Frederick Grant by name, voice, or context - when a live convergence needs historical/cultural contextualization without closure - when a field note, essay, chronicle, audio annotation, or interview needs Frederick's register - when a Remnant/Athenaeum comparison is appropriate - when an Elara counterweight pass is needed - when runtime probity after tic 230 is relevant (P2 manifold-shape closure, P1 signal-projection-split closure) - on explicit Architect invocation NOT WHEN: - when Breyden's direct voice is needed (use Architect register, not Frederick) - when Homeskillet's execution-layer voice is needed (use orchestrator register, not Frederick) - when the task is ordinary implementation (Frederick is composition, not patching) - when the task asks for legal accusation or definitive claims without evidence - when the user wants generic French style rather than Frederick's runtime - when the federation has not produced enough operational reality to warrant outside reading RELATES TO: - /complement (closure-inference sibling — both gate compositional integrity) - /consolidate (packaging neighbor — Frederick composes; consolidate packages) - publications/the-ubiquity-chronicles-fg.md (primary chronicle, v1, ~tic 175) - publications/the-ubiquity-chronicles-v2-frederick-grant.md (v2 expansion, Book Zero + Book I) - publications/the-ubiquity-chronicles-vol-iii-frederick-grant.md (Volume III — The Embodiment, tic 230) - publications/the-ubiquity-interviews-fg.md (interview register companion) - audit-logs/governance/p2-harmony-manifold-input-patch-receipt-tic230.md (P2 closure receipt) - audit-logs/governance/p1-signal-projection-split-receipt-tic230.md (P1 closure receipt) ARGS: stance: dispatch off_envelope: ask core_dispatch_rays: - "" → primary invocation (full 8-stage workflow) - "chronicles" → Ubiquity Chronicles composition - "parallel" → Parallel Lane Cadence composition - "field-note" → Field Notes script - "interview" → Interview script - "elara-pass" → Elara counterweight on existing draft - "anti-collapse" → Anti-collapse audit on existing draft - "tic230-probity" → Runtime probity composition secondary_modulation_axes: - register: chronicle | essay | field-note | interview | annotation - depth: lean | full - target: telos-internal | external-readership
tools
Runtime tactical context hydration — staged discovery and bounded source-bearing hydration for agent intent. Answers "how does an agent know where to look before it already knows where to look?" via filesystem shape, structural signals, and typed candidate baskets. Working acronym: RTCH (runtime-tactical-context-hydration). CENTROID: intent → bounded, source-reenterable evidence packet via staged source-bearing discovery IS: - structured intake of agent/Architect intent (goal, seeds, profile, fanout, mutation risk) - zone orientation (cwd / repo root / zone root / rung chain / obvious truth files) - low-cost shape scout (directory map, headings, durable handles, JSON/YAML keys, refs) - typed candidate basket with origin/use taxonomy and pairing rule enforcement - tactical probe plan (multiple bounded probes, not one giant regex) - bounded chunk hydration with line-range provenance and next-re-entry commands - agent-ready evidence packet emission (selected_surfaces, unresolved_questions, caution_map) - optional handoff to /consolidate for full-surface dump packaging IS NOT: collapse_zones: - vector database (no embedding-space retrieval; federation prohibits at federation rung) - semantic oracle (RTCH does not "understand" content; it surfaces structural signals) - doctrine engine (RTCH produces evidence; downstream consumers judge truth) - terrain engine replacement (federation cartography handles multi-plane semantic projection; RTCH is tactical layer beneath) - /consolidate rewrite (discovery and packaging do not collapse) - lossy compressor (bounded chunks preserve source re-entry; never summarize away source) - confidence-inflated smart consolidator sibling_overlaps: - /consolidate (RTCH selects; /consolidate packages — distinct boundaries; compose, don't replace) - file-access-discipline (RTCH outputs targets; hydration USES file-access-discipline as execution primitive) - load-doctrine-chain (both serve subagent context; load-doctrine-chain owns CLAUDE.md chain only, RTCH owns wider source set) - cache-ops (pattern source for trust-tier shape; storage NOT shared; RTCH packets are separate evidence cache) - queue_state_compile (analogy only — both convert append-only source to compiled view; different transforms) WHEN: - when agent intent is vague and discovery is needed before reading or consolidation - when bare grep would over-fanout or under-discover a vague target - when an arena, harpoon, /review, or other lane needs source-bearing evidence before action - when bounded chunk hydration is appropriate (large governance files, doctrine chains, audit history) - when the candidate-basket discipline (origin/use tagging, pairing rule) is needed to prevent generic-term overconfidence - when source re-entry must be preserved (consumer may need to return to source for fuller context) NOT WHEN: - when target is fully known (single file, single line range) — read it directly via file-access-discipline - when the operation is mutation-only on a known target (use Edit/Write directly) - when /consolidate has already been invoked with explicit targets (RTCH would re-do discovery) - when the operation requires semantic similarity (RTCH does not do that; federation prohibits vector DB) - when the consumer needs a packaged dump only (skip RTCH; /consolidate alone is sufficient if targets are known) - when promoting doctrine (route through /review; RTCH evidence may inform but does not promote) RELATES TO: - /consolidate (compose: RTCH selects targets; /consolidate packages selected_surfaces into dump with provenance reference back to RTCH packet) - file-access-discipline (compose: RTCH Stage 6 hydration USES file-access-discipline chunked-read as execution primitive) - load-doctrine-chain (compose: RTCH may invoke for doctrine_chain target_profile zone orientation) - zone_root.py (compose: RTCH Stage 2 anchors on zone-root walk-up) - atomic-append (compose: optional RTCH packet persistence uses atomic-append write hygiene) - queue_state_compile (analogous: both implement "raw source → compiled view" pattern) - /review preflight (downstream: future integration consumes RTCH packets as bench-packet discovery surface) - arena spec authoring (downstream: future integration uses RTCH packets for context preparation) - harpoon orchestrator (downstream: future integration uses RTCH for anchor-spot discovery on external binders) ARGS: stance: dispatch off_envelope: ask # off_envelope rationale: RTCH requires a structured intake to operate (goal, # target_profile, fanout_level, mutation_risk, expected_output, enough_evidence). # Bare invocation without intake fields would force the lane to guess discovery # scope, defeating the discipline. Ask elicits the missing fields. core_dispatch_rays: - "" → interactive (elicit intake form) - "--goal <sentence>" → with intake fields on CLI - "--intake <intake_json_path>" → from a saved/persisted intake - "--persist" → persist resulting packet to audit-logs/rtch/packets/ - "--handoff-to-consolidate" → after packet emission, hand selected_surfaces to /consolidate secondary_modulation_axes: - target_profile: doctrine_chain | audit_history | code_path | manifest_registry | vague_intent | mixed - fanout_level: conservative | normal | wide - mutation_risk: read_only | low_mutation | high_mutation - expected_output: hydration_packet | target_set_for_consolidate | single_chunk | claim_evidence IMPLEMENTATION_STATUS: binder: audit-logs/governance/runtime-tactical-context-hydration-binder.md (Phase 1 complete, tic 223) runner_script: NOT YET BUILT — Phase 2 deliverable (planned: cgg-runtime/scripts/rtch.py) current_mode: manual-discipline — agent walks the 8 stages using Read/Bash/Grep tools directly promotion_status: design lane, not doctrine; Phase 7 routes the doctrine question after Phase 6 validation
tools
Editorial intelligence scoring — reads transcripts the way a sharp editor would, scoring segments for shortform growth potential through the lens of audience context.
testing
Create, load, validate, and version show profiles and creative config objects for the podcast pipeline.