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/opsmill/infrahub-mcp/speckit.extractgit clone --depth 1 https://github.com/opsmill/infrahub-mcpWrote 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/opsmill/infrahub-mcp/speckit.extract)<a href="https://agentmods.dev/commands/opsmill/infrahub-mcp/speckit.extract"><img src="https://agentmods.dev/badge/commands/opsmill/infrahub-mcp/speckit.extract.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 5.1 | $0.00016 | $0.01397 |
| Opus 5 | $0.00008 | $0.00698 |
| Sonnet 5 | $0.00003 | $0.00279 |
| Haiku 4.5 | $0.00002 | $0.00140 |
Grade A, and why
speckit.extract 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 5d 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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
You MUST consider the user input before proceeding (if not empty).
Outline
- Phase 0: Setup & Validation
- Phase 1: Analysis & Classification
- Phase 2: Interactive Review
- Phase 3: Write Extractions
- Phase 4: Cleanup & Report
Phase 0: Setup & Validation
-
Determine target spec(s):
- If user provided a spec name: locate it in
.specify/orspecs/ - If no argument: scan for specs with status
implementedorcompleted - If no completed specs found: report and exit
- If user provided a spec name: locate it in
-
For each target spec, read:
spec.md(the specification)research.md(if exists — research notes from implementation)plan.md(if exists — implementation plan)tasks.md(if exists — task breakdown)
-
Read existing documentation to avoid duplicates:
dev/adr/— existing ADR filesdev/knowledge/— existing knowledge docsdev/guidelines/— existing guideline docs
-
Determine next ADR number from existing files in
dev/adr/.
Phase 1: Analysis & Classification
Step 1: Extract ADR candidates
Parse the spec and research files. For each significant decision:
- Extract: Decision, Rationale, Alternatives considered, Implementation pattern
- Determine if ADR-worthy:
- ADR-worthy: Affects system structure, API contracts, middleware composition, MCP protocol behavior, authentication patterns, or establishes a pattern used across multiple components
- Not ADR-worthy: One-off implementation detail with no broader implications
- Draft an ADR title (concise, decision-focused)
Step 2: Extract knowledge candidates
Identify content that documents how the system works:
- New architectural patterns or components
- Request/response flows
- Integration points with Infrahub SDK
- Middleware behavior changes
Determine target file: new doc in dev/knowledge/ or update to existing dev/knowledge/architecture.md.
Step 3: Extract guideline candidates
Identify content that prescribes how code should be written:
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.
- 5d ago First seen · 206 lines · 16 tokens per session scan A ee67e32e6abd
speckit.extract is a command published in the GitHub repository opsmill/infrahub-mcp (10 stars, last pushed yesterday), licensed Apache-2.0. It adds 16 tokens to every session and 1,397 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 2026-08-31.
Other commands, from other repositories
cl
Audit changelog entries before release.
awesome-chatgpt
Search awesome-ChatGPT-repositories for open-source GitHub repositories related to ChatGPT and LLMs.
/release
Release a new version — updates CHANGELOG, pyproject.toml, creates git tag, and pushes.
AGENTS
Per-command agent-optimized usage and structure guide.
bootstrap-memory
RUN { git ls-files; git ls-files --others --exclude-standard; } 2>/dev/null | sort -u | xargs wc -l 2>/dev/null | sort -rn | head -150 READ README.md.
pre-commit
Run pre-commit checks identical to GitHub CI (ruff, mypy, tests).