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 skills add arcasilesgroup/ai-engineering --skill code-auditgit clone --depth 1 https://github.com/arcasilesgroup/ai-engineeringWrote 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/skills/arcasilesgroup/ai-engineering/code-audit)<a href="https://agentmods.dev/skills/arcasilesgroup/ai-engineering/code-audit"><img src="https://agentmods.dev/badge/skills/arcasilesgroup/ai-engineering/code-audit/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/skills/arcasilesgroup/ai-engineering/code-audit"><img src="https://agentmods.dev/badge/skills/arcasilesgroup/ai-engineering/code-audit.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 | $0.00073 | $0.01504 |
| Opus 5.5 | $0.00029 | $0.00602 |
| Sonnet 5.5 | $0.00015 | $0.00301 |
| Haiku 4.5 | $0.00007 | $0.00150 |
Grade A, and why
code-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 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code audit
Find defects that will actually bite.
Read .claude/review/CONVENTIONS.md first — stack detection, scope, severity,
the false-positive gate, and the report format. The installed-version rule is
the single most important constraint here: verify against the installed source
before calling any framework or library API misuse. Most false positives in a
review like this come from reviewing the code as if it were an older version of
its framework.
Security is out of scope — that is security-audit. Accessibility is
a11y-audit, performance is perf-audit. Overlap is fine; do not go hunting
outside your lane.
What to look for
Ordered by how often each actually causes damage. Read files fully — the bug is usually in the interaction between two functions, not inside one.
1. Correctness
Logic that produces a wrong result: off-by-one and boundary conditions, inverted
or short-circuiting conditionals, null/nil/undefined reaching a dereference,
zero-values hitting a truthiness check that meant "absent" (0, "", empty
collection, false), index and slice assumptions, integer division and rounding,
timezone and DST handling, float comparison, mutation of shared or aliased state,
and the classic mutate-while-iterating.
2. Async, concurrency, and ordering Whatever this language's concurrency model is, the failure modes rhyme: operations awaited in the wrong order or not awaited at all; a result used before it is ready; two paths racing on shared state with no synchronization; a lock held across a suspension point or acquired in inconsistent order (deadlock); cancellation that leaves work half-done; retries that are not idempotent; a callback that closes over a value it expects to still be current and is not.
3. Resource and lifecycle management
Anything acquired must be released on every path including the error path:
file handles, sockets, DB connections and transactions, locks, subscriptions,
timers, listeners, watchers, background tasks. Look for a close/unsubscribe/
cancel that exists on the happy path only. In UI frameworks this is the
component-teardown path; in servers it is the request-error path.
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 · 131 lines · 73 tokens per session scan A 5acb51038ba1
code-audit is a skill published in the GitHub repository arcasilesgroup/ai-engineering (61 stars, last pushed 2d ago), licensed Apache-2.0. It adds 73 tokens to every session and 1,504 once invoked, about $0.0003 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 2026-09-12.
Other skills, from other repositories
pipeline-validator
Discovers, triggers, and monitors Azure DevOps pipelines (PR, Buddy Build, Buddy Release) for the current repo and branch. Auto-diagnoses failures from build logs, applies fixes, commits, pushes, and re-triggers until all pipelines pass or max retries reached. Validates PR existence and description completeness.…
ai-agents-empirical-probe-toolkit
Prove-it methods for this repo. Six recipes for runtime-contract probes, guard and threshold calibration, eval A/B, docs-vs-reality audits, reproduce-on-main CI triage, and negative-control test design, each with a worked example from repo history. Use when you say probe the runtime contract, calibrate this guard…
taste-lints
Use when you say run taste lints, check file size, or lint taste invariants. Custom lints with agent-readable remediation instructions for file size, naming conventions, structured logging, and complexity.
ai-agents-debugging-playbook
Symptom-to-triage playbook for this repo's recurring failures. Blocked pushes, drift gate reds, plugin bump reds, coverage pin trips, hook exit 143, session NONCOMPLIANT. Maps each symptom to a first command, discriminating experiment, fix path, and trap. Use when you say triage this failure, why is my push blocked…
ai-agents-config-catalog
Catalog of every configuration axis in this repo, env vars, commit markers, frontmatter keys, QA skip verdicts, and escape hatches, each with its enforcement point and abuse story, plus the checklist for adding a new flag safely. Use when you say what does a skip flag do, list escape hatches, can I skip this gate, add…
extension-audit-methodology
Systematic 5-dimension audit framework for VS Code extensions — debug hygiene, dead code, performance, menu validation, dependency cleanup.