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/buildgit 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 | $0.00597 |
| Opus 5 | $0.00000 | $0.00298 |
| Sonnet 5 | $0.00000 | $0.00119 |
| Haiku 4.5 | $0.00000 | $0.00060 |
Grade A, and why
build 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 — 21 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/aide:build — Build Phase
Agent: This command is executed by the
aide-implementoragent.
Execute the architect's implementation plan. This is the implementor phase in build mode — the session that turns plan.aide into working, tested code without making architectural decisions mid-session.
Checklist
- Read
plan.aidein the target module. This is the primary input — it names files, sequencing, and which existing helpers to reuse - Read
brief.aidein the same folder — the architectural-commitments file authored by the strategist during synthesize and refined by the architect during plan. Type shapes, exact strings, cross-module contracts, schema cardinality. Honor every commitment exactly. When a plan step says "honor commitment #11," #11 inbrief.aideis the source of truth - Check
## Prerequisites. If the plan declares prerequisites, verify they exist and export the expected contracts before writing any code. If a prerequisite is missing or doesn't match, stop and escalate back to the orchestrator — do not improvise - Read the intent spec (
.aideorintent.aide) for the target module. The plan tells you what to build;brief.aidetells you the architectural shape it must take; the intent spec tells you what counts as domain-correct - Execute the plan steps top-to-bottom. Check each checkbox in
plan.aideas you complete it. Do not reorder steps, skip steps, or add steps. If a step is ambiguous, stop and escalate back to the architect via/aide:planrather than inventing an answer - When build resolves an open question from
brief.aide, update the file: append a new numbered commitment capturing the resolution, remove the question from## Open questions. Numbers stay stable — do not renumber existing commitments - Write the code. No architectural improvisation — if a decision is not in
plan.aide,brief.aide, or.aide, it is out of scope for this session - Write tests covering every behavior the spec's
outcomes.desirednames, plus regression coverage foroutcomes.undesired. Tests are also where to assertbrief.aidecommitments the type system can't enforce alone (exact strings, schema cardinality, enum membership, parser rejection rules) - Run the tests until green
- Run the type checker (
tsc --noEmitor the project's equivalent) - Run
aide_validateto check for spec issues introduced during the build - Hand off to
/aide:qa— the QA agent will compare actual output against the spec'soutcomesblock (and consultbrief.aidefor structural clarification)
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 · 21 lines · 0 tokens per session scan A c3f192f64950
build 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 597 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].