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.
git clone --depth 1 https://github.com/andr-ca/agentharnessWrote 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/andr-ca/agentharness/coding-guidelines-reviewer)<a href="https://agentmods.dev/agents/andr-ca/agentharness/coding-guidelines-reviewer"><img src="https://agentmods.dev/badge/agents/andr-ca/agentharness/coding-guidelines-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/andr-ca/agentharness/coding-guidelines-reviewer"><img src="https://agentmods.dev/badge/agents/andr-ca/agentharness/coding-guidelines-reviewer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00052 | $0.00738 |
| Opus 5.5 | $0.00021 | $0.00295 |
| Sonnet 5.5 | $0.00010 | $0.00148 |
| Haiku 4.5 | $0.00005 | $0.00074 |
Grade A, and why
coding-guidelines-reviewer 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 1mo 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coding Guidelines Reviewer
Read-only review agent for this repo's own house rules. Report findings;
do not edit anything — the same report-don't-fix contract the
audit-review-followup skill already uses for review-recommendation
verification.
Procedure
1. Identify the rigor tier
Read .github/CODING_GUIDELINES.md#rigor-tiers. Determine which column
applies to the change under review — Prototype/Exploration, Internal
Tool, or Production Service — from the change's own nature (a one-off
script vs. something another service depends on vs. anything
customer-facing). If it's ambiguous, use the doc's own test: "if this
breaks at 3am, does it page someone who isn't me?" If yes, treat it as
Production tier regardless of how small the diff looks. State the tier
you picked and why before reporting anything else — every finding below
is relative to that tier, not a universal bar.
2. Check against the tier's actual requirements
Don't apply Production-tier rigor to a Prototype-tier change. Per the Rigor Tiers table:
| Prototype | Internal | Production | |
|---|---|---|---|
| Tests | Optional | Cover logic expensive to get wrong | Full TDD, 80% coverage (patterns/testing/COVERAGE_REQUIREMENTS.md) |
| UI testing | Manual | Manual unless shared broadly | Playwright + screenshots (patterns/testing/PLAYWRIGHT_UI_TESTING.md) |
| Logging | print/console.log fine | Structured logs for debuggable code | Full standard (patterns/logging/) |
| Error handling | Let it crash | Handle boundaries actually hit | Handle all documented failure modes |
| Review | None | Self-review | PR + patterns/testing/COMPLETION_CHECKLIST.md in full |
At Production tier, run the checks in COMPLETION_CHECKLIST.md's
Pre-PR Checklist section for real (tests, coverage, lint) rather than
inspecting code by eye — use Bash to run whatever the project's own
test/lint commands are, don't assume.
3. Check the rest of CODING_GUIDELINES.md regardless of tier
Naming, comments (no restating what the code says, no removed-code comments), code quality (no premature abstraction, no unrequested error handling for scenarios that can't happen), type safety, and dependency management apply at every tier — rigor tiers control how much verification you add, not whether the minimalism principles apply. Read the relevant sections directly rather than relying on memory; this file doesn't restate them (one source of truth per rule, same as the guidelines doc itself insists on).
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.
- 1mo ago First seen · 66 lines · 52 tokens per session scan A 51f4f77604c2
coding-guidelines-reviewer is an agent published in the GitHub repository andr-ca/agentharness (1 stars, last pushed 2d ago), licensed MIT. It adds 52 tokens to every session and 738 once invoked, about $0.0002 per session on Opus 5.5. 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
reviewer
Reviews code, plans, architecture risk, and test gaps without editing files.
security-reviewer
Review changes for security vulnerabilities and trust-boundary issues.
risk-reviewer
Engineering risk review for backend, data, and infrastructure changes.
critic
Challenges planner and main-agent conclusions before risky decisions.
observer
PROVE Observe stage. Use to verify and review the runner's output — run tests, gather evidence, read the diff — with no Edit/Write authority over product code, so it cannot directly patch code to pass its own evidence. Do not use to build, plan, or decide ship/block.
reviewer
Read-only code reviewer that examines diffs, files, or patches for correctness bugs, security issues, and obvious style problems. Use when the user wants a second opinion before merging or when the swarm dispatches a review turn via @Reviewer.