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.
npx agentmods add commands/gaia-react/gaia/speckit.specifygit clone --depth 1 https://github.com/gaia-react/gaiaWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/gaia-react/gaia/speckit.specify)<a href="https://agentmods.dev/commands/gaia-react/gaia/speckit.specify"><img src="https://agentmods.dev/badge/commands/gaia-react/gaia/speckit.specify.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00041 | $0.01376 |
| Opus 5 | $0.00020 | $0.00688 |
| Sonnet 5 | $0.00008 | $0.00275 |
| Haiku 4.5 | $0.00004 | $0.00138 |
Grade A, and why
speckit.specify 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/speckit-specify (GAIA preset)
This is the body that replaces the core speckit.specify command body when the GAIA preset is installed. The core specify body is inlined below at preset install time via the wrap strategy.
Step 0: GAIA pre-checks
The before_specify extension hook (registered by the GAIA extension) fires before this body runs. It enforces:
- Constitution placeholders are populated (
/speckit-constitutionfirst if not). - spec-kit version pin matches
requires.speckit_versionfrom.specify/extensions/gaia/extension.yml.
If the hook blocks, the agent halts here and surfaces the block message. Do not proceed past Step 1 in that case.
Step 1: core /speckit-specify
{CORE_TEMPLATE}
Step 1b: GAIA clarification contract (overrides the inlined core caps)
The core body inlined above (Step 1) carries its own clarification rules: a cap of "Maximum 3 [NEEDS CLARIFICATION] markers," a "max 3 total" limit on numbered questions, and an instruction to "present all questions together before waiting for responses." None of those apply in a GAIA project. Wherever the text above states any of them, this section supersedes it.
GAIA's clarification contract replaces all three:
- One question per turn. Ask exactly one question, then wait for the response. No multi-question forms, no "and also" clauses, never present a batch of questions together.
- No fixed question cap. The clarification budget and stop condition are GAIA's, governed by a coverage-based Socratic loop, not core's fixed limit of 3.
The authoritative sources for this contract are .specify/extensions/gaia/templates/clarify-prompts.md (Rule 1: one question at a time; Rule 8: the coverage-scan termination that decides when clarification stops) and .claude/skills/gaia/references/spec.md (the question ceiling and the one-question-per-turn hard constraint). The full GAIA Socratic clarify loop lives in /gaia-spec; a bare /speckit-specify run through this preset inherits this same one-question-per-turn contract, so the two never disagree in the agent's context.
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.
- 3d ago First seen · 86 lines · 41 tokens per session scan A f6a01c682bc2
speckit.specify is a command published in the GitHub repository gaia-react/gaia (22 stars, last pushed 3d ago), licensed MIT. It adds 41 tokens to every session and 1,376 once invoked, about $0.0002 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.
Other commands, from other repositories
pr-description
Generate a pull request description based on the changes in the current branch.
push-changes
If no topic provided, just document the recent changes. If a topic is provided, focus on documenting that topic.
create-PR
Command "create-PR" from bartstc/vite-ts-react-template, covering create a pr against this branch: $arguments, follow these steps and remember.
security-sast
Static Application Security Testing (SAST) for code vulnerability analysis across multiple languages and frameworks.
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.