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/aligngit 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 | $0.00663 |
| Opus 5 | $0.00000 | $0.00331 |
| Sonnet 5 | $0.00000 | $0.00133 |
| Haiku 4.5 | $0.00000 | $0.00066 |
Grade A, and why
align 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 yesterday.
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 — 25 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/aide:align — Alignment Phase
Agent: This command is executed by the
aide-aligneragent.
Verify spec-vs-spec alignment and brevity across the intent tree. This is NOT QA — QA checks code against a spec; alignment checks whether specs are consistent with their ancestors and internally tight against the Brevity Contract. The aligner runs three passes per walk:
- Cascade pass — child outcomes vs. every ancestor's outcomes; flags contradictions, undermining, omissions
- Brevity pass — every spec measured against the caps (description ≤ 200 chars, intent ≤ 100 words, 3-4 outcomes per list with ≤ 2 sentences each, body sections under cap, no forbidden content)
- Sibling-redundancy pass — content duplicated across siblings under a common parent; that content belongs in the parent
The aligner produces todo.aide at every misaligned node with concrete items tagged by misalignment type. Cascade and sibling-redundancy use Misalignment: spec-gap; brevity uses Misalignment: spec-bloat. The aligner never rewrites specs — it flags only.
Checklist
- Call
aide_discoveron the target path to get the full ancestor chain - Read each spec in the ancestor chain top-down via
aide_read— load description, intent, outcomes, and body sections at every level - Cascade pass: compare each child's
outcomes.desiredandoutcomes.undesiredagainst every ancestor's outcomes — look for contradictions, undermining, and critical omissions. Tag findingsMisalignment: spec-gap. - Brevity pass: measure every spec against the Brevity Contract caps and scan for forbidden content (type signatures, file paths, exact strings, function names, argument indexes, implementation contracts, migration history). Tag findings
Misalignment: spec-bloat. - Sibling-redundancy pass: at every parent with multiple children specs, compare children's content for material that appears in two or more. Flag the children (not the parent) with
Misalignment: spec-gap, naming the duplicated content and where it should live (parent). - For misaligned specs: set
status: misalignedon the leaf spec's frontmatter and producetodo.aideat the leaf with items from any pass that found drift - For aligned specs (no drift across all three passes): set
status: alignedon the spec's frontmatter - Report results with verdict (ALIGNED/MISALIGNED), count of specs checked, total drift count broken down by pass (cascade / brevity / sibling-redundancy), and
todo.aidepaths created - Recommended next step depends on the dominant category: cascade or sibling-redundancy →
/aide:specto revise the flagged specs; brevity →/aide:refactor --specs <path>for a batched cascade-aware sweep - Do NOT rewrite specs — flag only
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.
- yesterday First seen · 25 lines · 0 tokens per session scan A 987bc993bb8d
align 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 663 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].