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/aidemd-mcp/server/qagit clone --depth 1 https://github.com/aidemd-mcp/serverWhat 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 | $0.00000 | $0.00611 |
| Opus 5 | $0.00000 | $0.00305 |
| Sonnet 5 | $0.00000 | $0.00122 |
| Haiku 4.5 | $0.00000 | $0.00061 |
Grade A, and why
qa 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.
How it starts
The opening of the file, as written. The whole thing — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/aide:qa — QA Phase
Agent: This command is executed by the
aide-qaagent.
Verify actual output against the intent spec. This is the QA agent phase — the session that compares the spec's outcomes block against actual implementation and produces a todo.aide re-alignment document. See todo.aide spec for the file format.
Checklist
- Read the intent spec (
.aideorintent.aide) in the target module - Read
brief.aideif present — the architectural-commitments file. Use it to clarify what valid output looks like at the structural level when an outcome is ambiguous, and to verify the implementation didn't quietly diverge from a committed contract. You readbrief.aide; you do not modify it. - Focus on the
outcomesblock specifically:- Does the actual output satisfy every item in
outcomes.desired? - Does the actual output trip any item in
outcomes.undesired?
- Does the actual output satisfy every item in
- Check for hidden failures — outputs that pass tests but violate intent, missing edge cases the spec names, anti-patterns the spec warned against, implementation diverging from
brief.aidecommitments - Use judgement. If an output sounds wrong, reads wrong, or misses the point of the intent paragraph, flag it even when no specific outcome rule is named
- What you do NOT verify: items already enforced by the type system, by unit tests, or by code review — those run on every commit. Your concern is the failure mode none of them catches: technically valid output that violates intent
- Produce a
todo.aidenext to the spec. Useaide_scaffoldwith typetodoif none exists yet. Format:- Frontmatter:
intent(which outcomes are violated),misalignment(array of pipeline stages where intent was lost —spec-gap,research-gap,strategy-gap,plan-gap,implementation-drift,test-gap) ## Issues— each issue gets:- A checkbox
- A file path and line reference where the problem appears
- A one-line description of what's wrong
Traces to:whichoutcomesfield (desired or undesired) it violatesMisalignment:which pipeline stage lost the intent for this specific issue
## Retro— what would have caught this earlier? Which stage needs strengthening?
- Frontmatter:
- Do NOT propose solutions. The checklist says what's wrong and where — the implementor, invoked via
/aide:fix, decides how - Hand off to
/aide:fix— the implementor will work the checklist one item per session
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 · 28 lines · 0 tokens per session scan A 7d037c61adba
qa is a command published in the GitHub repository aidemd-mcp/server (3 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 611 tokens. 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
constitution
根据交互输入或已提供原则创建或更新项目章程，并确保相关模板保持同步。.
meta-theory-verify
Run the appropriate MetaKim verification path.
cross-research
Two-phase multi-model research. Phase A fans codex+gemini in parallel (benchmarks + citations angles); Phase B synthesises via fresh Claude session. Usage: /cross-research [--with | list | compare].
ijfw-audit
Run the IJFW audit gate for the current workflow phase. Usage: /ijfw-audit [phase name].
memory-why
Show why a memory recall returned what it did -- BM25 vs vector vs hybrid provenance.
ijfw-execute
Jump directly to the IJFW workflow Execute phase (Deep D4 / Quick Q3). Usage: /ijfw-execute [task or phase name].