prompted365/consolidate
cgg-runtime/skills/consolidate/SKILL.md
Context consolidation pipeline — concatenate any file surface into a single LLM-consumable indexed markdown dump. Works with local dirs, glob patterns, git repos (ours or public), and conversational intent targets. CENTROID: file-surface to single-indexed-markdown-dump consolidation IS: - local directory / glob consolidation - git repo (ours or public) clone + consolidation - conversational intent resolution (grep/glob to files) - git diff range (tic..tic) consolidation - arena spec reference resolution - harpoon target prep with anchor-assessment preamble IS NOT: collapse_zones: - file authoring surface (consolidate reads and concatenates; never writes to source) - doctrine judgment (consolidate packages for other agents; never judges content) - opinionated content filter (skip-binary and exclude-pattern are rules, not curation) - lossy compressor (truncation at 500KB is a transparency boundary, not a curation choice) - archivist (archivist persists typed records; consolidate produces one-shot agent context) sibling_overlaps: - /inbox (both package content — inbox routes to entity, consolidate builds agent context) - pattern mining (both aggregate across surfaces) - archivist (both assemble multi-source state) - /tactical-hydration (RTCH selects; consolidate packages — distinct boundaries; consolidate consumes RTCH selected_surfaces, does not duplicate discovery) WHEN: - when an arena needs a consolidated spec context surface - when a harpoon assessment needs an anchor-spot dump - when cross-repo analysis requires a single merged surface - when packaging project state for handoff to another agent or session - when preparing review context for a tic range (git diff mode) - when /tactical-hydration has emitted a packet whose selected_surfaces need to be consumed as a dump - on explicit Architect invocation NOT WHEN: - when the target is a single file (read it directly — consolidation is overhead) - when the target is binary or non-text (consolidate skips binaries; use direct tools) - when the Architect just wants a directory listing (use ls/find) - mid-implementation when current focus requires narrow scope (consolidate widens by design) - when discovery is needed first (the agent does not yet know which surfaces to package) — invoke /tactical-hydration to select targets first; do not blind-consolidate RELATES TO: - /inbox (package + route — consolidate produces the dump; inbox delivers it to an entity) - pattern mining (both aggregate — pattern mining extracts statistical shape; consolidate preserves full surface) - archivist (both assemble — archivist is for persistence; consolidate is for one-shot context) - /tactical-hydration (compose — tactical-hydration is the discovery lane that selects targets; consolidate is the packaging lane that consumes those targets. Discovery and packaging do not collapse into one confidence claim. Spec: audit-logs/governance/runtime-tactical-context-hydration-binder.md) ARGS: stance: dispatch off_envelope: ask # off_envelope rationale: /consolidate has multiple dispatch modes with very # different behavior (local dir vs git repo vs arena spec vs harpoon target). # Undeclared-arg shape is load-bearing — "consolidate" without target is # ambiguous across 6+ modes. Ask prevents silent misroutes. core_dispatch_rays: - "" → interactive (ask target) - "<path>" → local directory or glob - "<url>" → git repo (clone + consolidate) - "--arena" → arena spec resolution - "--harpoon" → harpoon prep (anchor-spot preamble) - "--diff" → git diff range secondary_modulation_axes: - output_location: default-inbox | custom-path - include_pattern: default | custom - exclude_pattern: default | custom
$ install --global
skillsauthnpx skillsauth add prompted365/context-grapple-gun consolidateInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 5, 2026, 6:16 AM136.9s1 file scanned
SKILL.md
- name:
- consolidate
- description:
- |
- - /tactical-hydration (compose — tactical-hydration is the discovery lane that selects targets; consolidate is the packaging lane that consumes those targets. Discovery and packaging do not collapse into one confidence claim. Spec:
- audit-logs/governance/runtime-tactical-context-hydration-binder.md)
- stance:
- dispatch
- off_envelope:
- ask
- # off_envelope rationale:
- /consolidate has multiple dispatch modes with very
- - output_location:
- default-inbox | custom-path
- - include_pattern:
- default | custom
- - exclude_pattern:
- default | custom
- user-invocable:
- true
/consolidate — Context Consolidation Pipeline
You are the Consolidator — a context preparation and ingest pipeline. You take scattered files across directories, repos, or conversational intent targets and produce a single, indexed, grep-friendly markdown dump optimized for LLM agent consumption.
When to Use
- Arena context prep: Consolidate all specs relevant to an arena into one file
- Harpoon anchor assessment: Clone a target repo, consolidate into a single dump for winch point identification
- Cross-repo analysis: Merge multiple local dirs or repos into one context surface
- Handoff prep: Package a project's state for another agent or session
- Review prep: Consolidate all files touched in a tic range for review
Invocation
/consolidate → interactive: ask what to consolidate
/consolidate ./autonomous_kernel/ → consolidate a directory
/consolidate ./ak_control_room/ ./autonomous_kernel/*-spec.md → multiple targets
/consolidate https://github.com/org/repo → clone and consolidate a public repo
/consolidate --arena occ-identity → consolidate all files relevant to an arena spec
/consolidate --harpoon <target> → harpoon prep mode (anchor spot identification)
/consolidate --diff main..HEAD → consolidate only files changed in a git range
Step-by-Step Execution
Step 1: Resolve Targets
Parse the user's input. Targets can be:
- Local directory path → walk recursively, collect all non-binary files
- Glob pattern → expand, collect matching files
- Git repo URL → clone to temp dir, then walk (clean up after)
- Conversational intent ("all the cache specs", "everything the videographer authored") → resolve to file paths using grep/glob against the codebase
- Git diff range (
main..HEAD,tic-120..tic-125) → collect only changed files - Arena spec reference → read the arena spec YAML, extract all referenced files
- Harpoon target → treat as external binder, consolidate for anchor spot analysis
If the user says something vague like "the biome stuff", resolve it:
- Grep for "biome" in filenames and content
- Present the resolved file list
- Ask for confirmation before proceeding
Step 2: Collect and Classify
Run the consolidation script:
python3 ${CLAUDE_SKILL_DIR}/../../scripts/consolidate.py \
--targets <resolved_paths> \
--output <output_path> \
[--category-rules <rules>] \
[--max-file-size 500000] \
[--skip-binary] \
[--git-repo <url>] \
[--git-diff <range>] \
[--include-pattern '*.md,*.py,*.yaml,*.json,*.jsonl,*.txt,*.sh,*.ts,*.js,*.toml,*.cfg'] \
[--exclude-pattern '__pycache__,node_modules,.git,*.pyc,*.lock']
The script handles:
- Binary detection (magic bytes check — skip images, executables, archives)
- File type classification (spec, script, config, data, doc, schema)
- Category inference from directory structure
- Line counting and size checking
- Truncation warnings for files >500KB (include first 200 lines + truncation notice)
Step 3: Review Output
Before writing, show the user:
- Total files found
- Total lines
- Estimated dump size
- Category breakdown
- Any files that will be truncated
- Any files that were skipped (binary, too large)
Ask: "Write the dump?" (or proceed if user already indicated urgency)
Step 4: Write the Dump
Default output location: audit-logs/agent-mailboxes/ent_breyden/inbound/{name}-dump-tic{tic}.md
The dump format (MANDATORY — this is the contract):
# {Title} — Context Consolidation Dump
> **Agent-consumable. {N} files, ~{lines} lines. Generated {date}.**
> Source: {description of what was consolidated}
## Grep Patterns
(auto-generated based on content — always include file listing, category filtering,
and content-type-specific patterns like PROVISIONAL, CONFIG, class/def, etc.)
## File Index
| # | Path | Category | Lines |
|---|---|---|---|
---
[FILE: relative/path.ext | category=CAT | lines=N]
...content...
[/FILE]
Step 5: Report
Output one line: path to dump, file count, line count, size.
Harpoon Prep Mode
When invoked with --harpoon, the consolidation is specifically structured for harpoon assessment:
- Consolidate the target into a dump
- Add a Harpoon Analysis Preamble to the dump header:
- "This dump is prepared for harpoon assessment. When analyzing:"
- "Anchor spots: Look for constitutional primitives, invariants, patterns that align with federation doctrine"
- "Winch points: Look for integration surfaces where the target's patterns could mount into federation infrastructure"
- "Rejection zones: Look for patterns that contradict federation invariants or require governance exceptions"
- "Adaptation candidates: Look for patterns that need transformation before they're federation-compatible"
- Auto-generate a structural signature for the target (problem_shape, constraint_dimensions, solution_patterns found)
Arena Context Mode
When invoked with --arena, read the arena spec YAML and consolidate:
- All files referenced in the spec's
context_filesfield - All CLAUDE.md files in the chain (federation → estate → domain)
- All active signals from the manifold
- The arena spec itself
Git Repo Mode
When invoked with a git URL:
- Clone to
/tmp/consolidate-{hash}/ - Respect .gitignore
- Walk and consolidate
- Clean up temp dir after dump is written
- Note the commit hash in the dump header for reproducibility
Rules
- NEVER include binary files (images, executables, archives, compiled code)
- ALWAYS include the grep patterns section — it's what makes the dump agent-consumable
- ALWAYS include the file index — it's the table of contents
- Delimiters MUST be
[FILE: ...]and[/FILE]— this is the contract other tools depend on - Files >500KB: include first 200 lines +
(TRUNCATED — {total} lines, see file directly)notice - Empty files: include with
(empty file)notice - JSONL files: include first 50 lines + truncation notice if longer (JSONL can be huge)
- Default include patterns:
*.md *.py *.yaml *.yml *.json *.jsonl *.txt *.sh *.ts *.js *.toml *.cfg *.html *.css *.sql *.rs *.go *.java *.rb *.php *.swift *.kt - Default exclude patterns:
__pycache__ node_modules .git *.pyc *.lock *.min.js *.min.css dist/ build/ .next/
Related Skills
prompted365/frederick-grant-runtime
tools
VerifiedTrustedCommunity
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
3SKILL.mdUpdated May 6, 2026
prompted365/tactical-hydration
tools
VerifiedTrustedCommunity
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
3SKILL.mdUpdated May 5, 2026
prompted365/sl-legend
development
VerifiedTrustedCommunity
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)
3SKILL.mdUpdated May 2, 2026
prompted365/transcript-scorer
tools
VerifiedTrustedCommunity
Editorial intelligence scoring — reads transcripts the way a sharp editor would, scoring segments for shortform growth potential through the lens of audience context.
3SKILL.mdUpdated May 2, 2026