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/andr-ca/agentharness/coding-guidelines-reviewergit clone --depth 1 https://github.com/andr-ca/agentharnessWhat 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 | $0.00052 | $0.00738 |
| Opus 5 | $0.00026 | $0.00369 |
| Sonnet 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 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 — 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.
- yesterday 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 $0.0003 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
design-interaction
Interaction Designer on the Atlas bench. Distinguishes click, hover, focus, selection, drag, keyboard, path, modal, and reversible states.
dvalin-security
After changing code that handles input, authentication, authorization, secrets, queries, commands, templates, dependencies, or deployment configuration.
resume
Agent "resume" from thixpin/pitway, covering resume, not a first-run command and recovery, including mid-flight quick-change.
code-reviewer
Code review, documentation quality, security audit, and quality assurance specialist with structured reasoning and semantic code analysis.
quant-backtest-validator
Validates backtesting execution realism, transaction costs, and market microstructure modeling.
lemoncrow-solve
Always use for autonomous verified task solver.