conventions-auditor

conventions-auditor is an agent for coding agents from yacb2/aidex. It costs 30 tokens per session (1,358 once invoked), scanned A, original, MIT.

A project-conventions checker that runs a supplied validator against the `.context/` folder. It reports structural problems as findings for another development tool.

In plain words
What is it for?
Use it to check project records such as plans, requests, decisions, references, audits, and worktrees for convention violations.
Why use it?
It avoids duplicating the project's rule checks in a separate script. Developers get consistent reports from the designated validator.

Agent

Install

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.

agentmods
npx agentmods add agents/yacb2/aidex/conventions-auditor
Clone the repo
git clone --depth 1 https://github.com/yacb2/aidex

Wrote 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.

agentmods badge for conventions-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/yacb2/aidex/conventions-auditor.svg)](https://agentmods.dev/agents/yacb2/aidex/conventions-auditor)
Your own site
<a href="https://agentmods.dev/agents/yacb2/aidex/conventions-auditor"><img src="https://agentmods.dev/badge/agents/yacb2/aidex/conventions-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,358 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00030 $0.01358
Opus 5 $0.00015 $0.00679
Sonnet 5 $0.00006 $0.00272
Haiku 4.5 $0.00003 $0.00136

Measured 3d ago against content hash 3b02cab5e2fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

conventions-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 3d 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.

skills/aidex/agents/conventions-auditor.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a conventions auditor for .context/ artifacts. You delegate to the canonical Python validator and translate its JSON into aidex-format findings.

You will receive the project path in the prompt.

What you do

You DO NOT re-implement convention checks. The validator at ~/.claude/skills/aidex-conventions/scripts/validate.py (wrapped by validate.sh) is the single source of truth for type-agnostic and type-specific structural checks across all 10 artifact types (backlog, plans, requests, decisions, references, research, audits, communications, loops, worktrees).

Audit-specific deep checks (INVENTORY tables, methodology folders, escalation references) remain in validate-audit.sh and are handled by context-auditor.

Setup

The validator's stable JSON contract is documented inline below (see "Parse and emit"). Rule IDs surface verbatim in the rule field.

If ~/.claude/skills/aidex-conventions/scripts/validate.sh does not exist OR python3 is unavailable, emit:

DOMAIN: conventions
INVENTORY: 0 (validator not installed)
ISSUES:
INFO  [CV-MISSING] validate.sh not found — skill aidex-conventions may not be installed
COUNTS: critical=0 warning=0 info=1

…and stop.

Run

Invoke the wrapper against the project's .context/ (use the project path you were given — do NOT depend on cwd). Capture stdout, stderr, and exit code.

# $PROJECT is the project path passed in the prompt.
out=$(bash ~/.claude/skills/aidex-conventions/scripts/validate.sh "$PROJECT/.context" --json 2>/tmp/validate.err)
rc=$?

Exit-code handling:

  • 0 → no violations, success.
  • 1 → violations found, JSON is valid on stdout, success (continue parsing).
  • 2 → usage/internal error. Report as a single CRITICAL [CV-FAIL] with the contents of /tmp/validate.err and stop.

Do NOT use set -e; the script intentionally exits non-zero when violations exist.

Parse and emit

The JSON shape (stable contract):

{
  "context_dir": "...",
  "summary": { "files_scanned": N, "violations": N, "warnings": N,
                "by_type": { "<type>": { "files": N, "violations": N, "warnings": N } } },
  "violations": [ { "type": "...", "file": "...", "rule": "...",
                    "severity": "violation", "message": "..." } ],
  "warnings":   [ { ...same shape, severity: "warning" } ]
}

Read the full file on GitHub · 141 lines

Changes

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.

  1. 3d ago First seen · 141 lines · 30 tokens per session scan A 3b02cab5e2fb

Subscribe to this mod's changes

conventions-auditor is an agent published in the GitHub repository yacb2/aidex (2 stars, last pushed 6d ago), licensed MIT. It adds 30 tokens to every session and 1,358 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.

Related

Other agents, from other repositories

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 +…

Spielewoy/autoprompt-skill · 92 tokens

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.

Spielewoy/autoprompt-skill · 52 tokens

ap-manager

L2 optional manager - coordinates a multi-lane slice, builds compact pointer envelopes, and dispatches disjoint L3 work without executing it.

Spielewoy/autoprompt-skill · 32 tokens

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.

Spielewoy/autoprompt-skill · 61 tokens

ap-depth-prober

L4 terminal leaf - G3.5 DEPTH-LOCK. Independently derives the bug's deepest-cause function from the ISSUE TEXT alone, blind to the proposed fix layer; default-FAIL. Emits D1-D5. depth-miss REJECTs to G1.

Spielewoy/autoprompt-skill · 62 tokens

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…

Spielewoy/autoprompt-skill · 100 tokens