codex/skills/spec-gate/SKILL.md
Decide whether a grill/handoff packet is complete enough for `$plan`, spec generation, or downstream mutation. Use for `$spec-gate`, is this ready to plan, block planning, handoff packet, decision packet, premature specs, no-grill justification, mutation gate, or underspecified questions, proof bar, scope, non-goals, rollout/rollback, and receipts.
npx skillsauth add tkersey/dotfiles spec-gateInstall 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.
Prevent $plan from discovering the objective and prevent mutation from outrunning decisions.
A plan is allowed only when the handoff packet is decision-complete or every remaining gap is explicitly assumed, deferred, owned, and defaulted.
Downstream mutation is allowed only after a complete spec has also passed invariant challenge, fresh-eyes pass, and lint. A pre-spec gate can allow planning while still keeping mutation_allowed: false.
Planning is allowed only when this sentence can be completed concretely:
We are building X, for Y, by changing Z, while explicitly not doing A/B/C, and success means P/Q/R proofs pass.
grill_rounds > 0 or concrete no_grill_justificationReturn PLAN_ALLOWED: false when any of these are true:
grill_rounds: 0 and no concrete no_grill_justification is present;Emit MUTATION_ALLOWED: false for handoff-only gates unless the input already includes:
When only a decision packet is being gated, planning may be allowed while mutation remains blocked.
PLAN_ALLOWED: true|false
MUTATION_ALLOWED: true|false
strictness_profile: fast|balanced|strict|campaign
missing_fields:
material_open_questions:
blocking_risks:
recommended_defaults:
clarification_receipt:
next_grill_questions:
Ask at most 1-3 next grill questions, each with a stable snake_case id and bounded choices.
For handoff packets saved to disk:
python codex/skills/spec-gate/scripts/spec_gate.py --strict-receipts path/to/handoff.md
The script is a conservative structural check. The model must still judge semantic completeness.
tools
Invokes Apple's macOS 27 fm command-line tool from a local Mac to use the on-device system model or Private Cloud Compute, including instructions, image prompts, schema-constrained JSON, and noninteractive automation. Use when the user asks to run Apple Foundation Models through fm, compare system versus pcc, generate structured output, or automate fm without Swift or an app.
development
Compile historical Codex sessions into governed counterfactual evidence, evaluate an existing owner-applied candidate through blinded paired HCTP trials, and fold observable evidence into RUN, OBSERVE, or STOP. Use for `$hylo`, CRF extraction, counterfactual replay, source-governed direct or historical trials, sealed evidence, paired baseline/candidate evaluation, causal frontiers, or evidence-governed improvement.
testing
Ensure a `ledger` command is available on PATH; materialize, validate, record, replay, and project requested Actuating artifacts without taking semantic or execution authority; coordinate the shared Learnings/Synesthesia/Negative Ledger lifecycle checkpoint and repo-local source-memory reconciliation; address Universalist plans and receipts; and perform pure artifact validation.
testing
Classify and quotient review findings, failing tests, incidents, bug reports, migration failures, and other witnessed falsifiers against accepted intent and the current Construction. Author counterexample-set/v1 without selecting repairs, counting review credit, or granting mutation.