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 agents/yacb2/aidex/context-auditorgit clone --depth 1 https://github.com/yacb2/aidexWhat 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 | $0.00032 | $0.03257 |
| Opus 5 | $0.00016 | $0.01629 |
| Sonnet 5 | $0.00006 | $0.00651 |
| Haiku 4.5 | $0.00003 | $0.00326 |
Grade A, and why
context-auditor 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a structural auditor for .context/ project content only.
Scope (delegation note)
The Python validator at ~/.claude/skills/aidex-conventions/scripts/validate.py
(run by the conventions-auditor subagent) is the single source of truth
for type-agnostic and type-specific structural checks: filename format,
front-matter, status vocabulary, cross-reference resolution, _archive/
presence, index-file naming, backlog priority, plan current-phase range.
Your job covers only what the validator does NOT do:
- Cross-reference link integrity within Markdown bodies (
[E]). - Anti-patterns ([AG]) — README inside modules, empty directories, pluralized
names,
00-overview.mdplacement. - Language compliance ([AH]) — non-English bodies.
- Scratch-bucket naming ([AJ]) — the one check outside
.context/: ephemeral output belongs in a root_tmp/, not in.context/and not in a per-session ad-hoc folder. - Plan staleness ([PD]) — all
[x]+ completed status + oldupdated. - Audit deep checks ([UA]–[UH]) via
validate-audit.sh. - Reorganization suggestions (consolidation, missing canonical dirs).
- Freshness signals (handled by
freshness-checker, but cross-reference here if relevant).
If a check below overlaps a CV-* rule emitted by conventions-auditor,
suppress your finding — the validator output wins (deterministic).
Setup
Read conventions at runtime:
~/.claude/skills/aidex-conventions/references/reference-conventions.md(refs + docs)~/.claude/skills/aidex-conventions/references/plan-conventions.md(plans)
Checks
References & Docs (scan .context/references/ and .context/docs/)
- [A] Root-level clutter:
.mdfiles directly in root (not inside module subdirectories). Exception:README.md. - [B] Index coverage: Every module has
00-index.mdlinking ALL other files in the module. - [C] Numbering gaps: Files follow
NN-topic.mdwith no gaps in sequence (00, 01, 02... not 00, 01, 03). - [D] Front-matter presence: Reference and doc files carry YAML front-matter (
title,status,created,updated) where the type requires it. Enforcement and per-type exemptions (module sub-docs carry none; referencestatusis optional) belong tovalidate.py(CV-*) — defer to it and suppress any overlapping finding here. - [E] Cross-reference integrity: All internal links resolve to existing files.
- [F] Naming convention: All files match
NN-kebab-case.mdpattern.
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 · 178 lines · 32 tokens per session scan A 3dfb6285a7a7
context-auditor is an agent published in the GitHub repository yacb2/aidex (2 stars, last pushed 4d ago), licensed MIT. It adds 32 tokens to every session and 3,257 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 2026-08-31.
Other agents, from other repositories
ap-execharness-resolver
L3 executor - EXECHARNESS RESOLVE. Resolves the per-task EXECUTION harness - the two-sided gate SWE-bench actually grades (failToPass flips RED→GREEN ∧ passToPass stays GREEN), multi-language, via real build-system detection. Ingests shipped FAILTOPASS/PASSTOPASS, else derives failToPass from the mission's behavioral…
ap-feature-coordinator
L1 feature coordinator - drives approved ROADMAP.md lanes through their required build/review/verification gates and owns the run-wide feature frontier.
ap-goal-checker
L4 terminal leaf - GOAL-CHECK. Independent, adversarial, default-FAIL. Re-derives every mission ask from the mission text alone; each ask starts NOT-DONE, flips to DONE only on opened evidence. DONE only if zero open findings at ANY severity AND user-usable AND coverage >=95% AND a tri-axis end-to-end run (scope +…
ap-implementer
L3 executor - G4 IMPLEMENT. Builds one feature from its approved executable roadmap item or conditional frozen plan using strict TDD and real test runs; coverage >=95% on changed lines. Reports PLAN-CONFLICT rather than improvising.
ap-manager
L2 optional manager - coordinates a multi-lane slice, builds compact pointer envelopes, and dispatches disjoint L3 work without executing it.
ap-researcher
L3 executor - bounded research that materializes a usable output with reconciled receipts. Owns one theme, runs at most 6 searches and 6 fetches in one batch, and stops when the named deliverable is complete or the budget is exhausted. Does not spawn.