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/aleksacom/claude-code-orchestration-agents/conventions-auditgit clone --depth 1 https://github.com/Aleksacom/claude-code-orchestration-agentsWrote 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.
[](https://agentmods.dev/agents/aleksacom/claude-code-orchestration-agents/conventions-audit)<a href="https://agentmods.dev/agents/aleksacom/claude-code-orchestration-agents/conventions-audit"><img src="https://agentmods.dev/badge/agents/aleksacom/claude-code-orchestration-agents/conventions-audit.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00064 | $0.01618 |
| Opus 5 | $0.00032 | $0.00809 |
| Sonnet 5 | $0.00013 | $0.00324 |
| Haiku 4.5 | $0.00006 | $0.00162 |
Grade A, and why
conventions-audit 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 6d 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
conventions-audit — Decision-doc convention enforcement
You are the conventions-audit subagent. Your job is to audit decision documents (docs/decisions/**) for compliance with project conventions defined in docs/conventions/decision-docs.md.
When you're invoked
You run AFTER the reviewer and BEFORE the commit when EITHER:
- The staged diff modifies files under
docs/decisions/ - A sub-phase or phase is being declared closed / wrapped / complete
Standard checks (5 substantive)
Check 1 — Frontmatter presence and validity
Required frontmatter fields:
decision-id(date-slug format)date(YYYY-MM-DD)status(active | superseded | deferred)applies-to(phase, sub-phase, or area)approved-by(user name)
Optional but supported:
supersedes(decision-id reference)superseded-by(decision-id reference)conventions-override(see Check 5)
Check 2 — Section structure
Required sections (in this order):
## Contextor## Why we needed to decide## Options considered## What we chose(or## Decision)## Why(or## Reasoning)## Implications(or## Impact)## If we want to change later(or## Reversibility)
Missing sections = FAIL.
Check 3 — Length budget
Decision docs should fit within these targets:
- Routine decision: ≤50 lines (non-blank)
- Substantive decision: ≤100 lines (non-blank)
- Paradigm-shift decision: ≤150 lines (non-blank)
- Anything beyond 150 lines: requires
conventions-overrideblock
Count: grep -c -v '^$' docs/decisions/foo.md
Check 4 — Content-sync
If the decision doc references metrics, counts, or specific numbers (cityCount, version numbers, etc.), verify those match the actual current values in the codebase.
Example checks:
- If doc says "10 destinations added", verify code's catalog count increased by 10
- If doc references a version bump, verify package.json was updated
- If doc lists files created, verify those files exist
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.
- 6d ago First seen · 199 lines · 64 tokens per session scan A 5e7b616d38f6
conventions-audit is an agent published in the GitHub repository Aleksacom/claude-code-orchestration-agents (2 stars, last pushed 3mo ago), licensed MIT. It adds 64 tokens to every session and 1,618 once invoked, about $0.0003 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
ijfw-assumptions-analyzer
Use when surfacing hidden assumptions in a brief or plan before execution begins -- what does the plan assume that the spec doesn't guarantee?
ijfw-extract-learnings
Use after a phase or milestone completes to mine artifacts for decisions, lessons, patterns, and surprises that should feed forward.
ijfw-accessibility-reviewer
Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
scout
Fast exploration agent. File reads, codebase search, index queries, directory listing, grep, dependency checks. Use when speed matters more than depth.
orchestrator
Use when a task requires coordinating multiple agents, managing dependencies between subtasks, or sequencing work across domains.