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 skills/andr-ca/agentharness/code-reviewnpx skills add andr-ca/agentharness --skill code-reviewgit 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 | $0.00056 | $0.04861 |
| Opus 5 | $0.00028 | $0.02431 |
| Sonnet 5 | $0.00011 | $0.00972 |
| Haiku 4.5 | $0.00006 | $0.00486 |
Grade A, and why
code-review 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 — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review
A systematic approach to reviewing diffs and pull requests. Work through the categories below in order — correctness first, style last.
Pre-read checklist
Before reading the diff:
- Read the PR description. Does it explain why the change is needed? If the description is missing or just "fixes stuff", ask for one before reviewing — the diff alone won't tell you whether the approach is right.
- Check the linked issue or ticket if there is one.
- Note the rigor tier (
patterns/profiles/or.agentharness-profile) — the coverage and testing requirements differ.
1. Correctness
The most important category. Ask: "Can this code produce wrong results?"
- Does the logic match the stated goal?
- Are there off-by-one errors, wrong comparisons, or incorrect assumptions about the data?
- Are all inputs validated before use?
- Are edge cases handled: empty collections, zero, null/None/undefined, negative numbers, max values, concurrent access?
- Does error handling actually handle the error, or does it swallow it silently?
- Are exceptions caught at the right level (not too broad, not too narrow)?
- Are resources (files, connections, locks) released even on exception?
# Swallowed error — caller sees success, wrong data silently used
try:
value = parse_config(raw)
except Exception:
pass # WRONG: value is now unset or stale
# RIGHT: propagate or at minimum log + re-raise
try:
value = parse_config(raw)
except ConfigError as e:
logger.error("config parse failed", error=e)
raise
2. Security
Run through the relevant items from the security-review skill (load it
for the full checklist). The most common PR-level findings:
- Secrets or API keys hardcoded or logged.
- SQL/shell/HTML built via string formatting with user input.
- Missing ownership/permission checks on resource access.
- New dependency with known CVEs (
npm audit/pip-auditnot run).
3. Test coverage
At Production tier, new code must have tests. Check:
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 · 290 lines · 56 tokens per session scan A d2343eb00aba
code-review is a skill published in the GitHub repository andr-ca/agentharness (1 stars, last pushed yesterday), licensed MIT. It adds 56 tokens to every session and 4,861 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 skills, from other repositories
html-ppt-zhangzara-coral
OpenDesign's community-growth campaign across GitHub, Discord, and X: the loops, the content calendar, and the pipeline math. Built as a decision-grade marketing & GTM deck for growth team, community lead.
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
deepstream-sop
Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated FastAPI service that detects whether operators perform assembly-line steps in order via event boundary detection (GEBD) plus VLM classification. Trigger even if the…
cupynumeric-migration-readiness
Pre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment…