An automatic check that reviews a newly written software specification for forbidden changes to its required rules. A software specification describes what a feature must do.

Use it as a required post-specification check in projects using spec-kit or the GAIA preset.

It catches accidental edits to requirements immediately after the specification is created.

lint — Command by gaia-react

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add commands/gaia-react/gaia/lint

Clone the repo

git clone --depth 1 https://github.com/gaia-react/gaia

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 853 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00018	$0.00853
Opus 5	$0.00009	$0.00426
Sonnet 5	$0.00004	$0.00171
Haiku 4.5	$0.00002	$0.00085

Measured 2d ago against content hash d4f8e23d9473, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lint scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.specify/extensions/gaia/commands/lint.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Immutability lint pass

Fired automatically by spec-kit on the after_specify event (mandatory hook). The agent reads this skill and audits the SPEC that /speckit-specify (or the GAIA preset's wrap) just produced.

Locate the artifact

The lint target is the SPEC artifact written by the preceding /speckit-specify invocation. In a GAIA project the preset redirects writes into .gaia/local/specs/SPEC-NNN/SPEC.md; in a bare spec-kit project the artifact lives at specs/<NNN>-<slug>/spec.md.

Resolve the path in this order:

If $ARGUMENTS carries an explicit path, use it.
Otherwise inspect .gaia/local/specs/SPEC-*/SPEC.md for a SPEC file modified within the last five minutes (the just-written artifact).
Otherwise fall back to .specify/feature.json (spec-kit's pointer to the active feature directory) and resolve <feature-dir>/spec.md.

If no candidate resolves, surface:

after_specify lint skipped: no SPEC artifact found at expected paths.

Run the lint helper

Run using the Bash tool:

bash .specify/extensions/gaia/lib/lint.sh <resolved-spec-path>

The helper emits a JSON result on stdout: {"ok": true, "findings": []} on pass; {"ok": false, "findings": [...]} on fail. Exit codes: 0 pass, 1 fail, 2 usage error.

Surface results

Pass. Emit:

after_specify lint passed:
Fail. Emit each finding's code, message, and where field on its own line. Then announce:

after_specify lint failed: finding(s). Fix the SPEC and re-run, or invoke /gaia-spec again to amend before save.
Usage error (exit 2). Treat as a tooling problem, not a SPEC problem; report the stderr message and skip the lint without blocking the lifecycle.

What the helper checks (reference; helper is the source of truth)

Frontmatter present and well-formed.
Required keys: spec_id, type, status, immutable, wiki_promote_default, chain_trigger, intent, success_criteria, uats, scope_boundaries, clarifications, research_summary, created, updated.
immutable: true.
status ∈ {in-progress, reopened, closed}.
spec_id matches SPEC-NNN.
Every UAT entry has a frozen uat_id: UAT-NNN.
No placeholder text ([PLACEHOLDER], <TODO>, <TBD>, FIXME, bare TBD).
For status: reopened: body contains ## Reopen rationale and ## UAT diff sections (the reopen ceremony).

Read the full file on GitHub · 62 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2d ago First seen · 62 lines · 18 tokens per session scan A d4f8e23d9473

Subscribe to this mod's changes

lint is a command published in the GitHub repository gaia-react/gaia (22 stars, last pushed 2d ago), licensed MIT. It adds 18 tokens to every session and 853 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

eslint msw prettier storybook stylelint

lint

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Immutability lint pass

Locate the artifact

Run the lint helper

Surface results

What the helper checks (reference; helper is the source of truth)

What this file has done since we first saw it

Other commands, from other repositories

pr-description

push-changes

create-PR

security-sast

git

checklist