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/Kin9Zeus/senior-engineer-skillsWrote 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/commands/kin9zeus/senior-engineer-skills/snr-audit)<a href="https://agentmods.dev/commands/kin9zeus/senior-engineer-skills/snr-audit"><img src="https://agentmods.dev/badge/commands/kin9zeus/senior-engineer-skills/snr-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/commands/kin9zeus/senior-engineer-skills/snr-audit"><img src="https://agentmods.dev/badge/commands/kin9zeus/senior-engineer-skills/snr-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 | $0.00026 | $0.00683 |
| Opus 5 | $0.00013 | $0.00342 |
| Sonnet 5 | $0.00005 | $0.00137 |
| Haiku 4.5 | $0.00003 | $0.00068 |
Grade A, and why
snr-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 12d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Senior Engineering Audit
Run a full-spectrum audit of $ARGUMENTS (default: the current repository).
Load the project-audit skill and follow it exactly. Load senior-engineer for
the discovery protocol and the severity rubric.
Depth
--quick— the 30-minute triage inproject-audit/references/quick-scan.md. Domains 1, 2, 3 and 11 at depth; the rest as a one-line status. Say explicitly that this is not a full audit.- (default) — Standard. All fifteen domains, depth proportional to weight.
--deep— All fifteen at depth, plus a threat model, a restore-drill request and a load-test recommendation.
Parallelising
--parallel is an explicit authorisation to dispatch concurrent domain
reviewers. When passed, run these as independent subagents and merge the
findings, giving each one the Ground Truth block so nobody re-derives it:
- Security and supply chain — load
security-hardening - Data and persistence — load
database-engineering - Testing and correctness — load
testing-strategy - Web presence, accessibility and privacy — load
web-presence-audit,accessibility-audit,privacy-compliance - Platform, observability and performance — load
devops-platform,observability-slo,performance-engineering
Without --parallel, run the passes yourself, in weight order.
Before anything else
- Confirm scope. Repository only, or also the live site and infrastructure? Never send traffic to infrastructure the user has not confirmed they own or are authorised to test.
- Confirm what may be run. Read-only analysis is always safe. Ask before installing dependencies, running tests, or starting services.
- Run
skills/project-audit/scripts/recon.sh(orrecon.ps1) if the environment allows. It is read-only.
Output
Use project-audit/templates/audit-report.md. Write it to
AUDIT-<YYYY-MM-DD>.md if it is longer than a screen, and offer to publish it
as a shareable artifact.
Every finding: what is wrong → why it matters concretely → the fix → how to
verify the fix, with a file:line location and a CONFIRMED/PLAUSIBLE
label.
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.
- 12d ago First seen · 70 lines · 26 tokens per session scan A e611f655b506
snr-audit is a command published in the GitHub repository Kin9Zeus/senior-engineer-skills (3 stars, last pushed 18d ago), licensed MIT. It adds 26 tokens to every session and 683 once invoked, about $0.0001 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 commands, from other repositories
critique
Adversarial design critique of the current work — render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.
review-my-code
Review code for bugs, security issues, and clarity, with severity-ranked findings and concrete fixes.
code-review
OWASP-mapped, skill-aware code review with autofix suggestions. Reviews the diff, not the world.
bugfix
IMPORTANT: You MUST run this shell command FIRST before doing anything else.
unwired
Scans the whole codebase for implementations that exist but are never wired in — and for wired implementations left incomplete — then, per finding and only with explicit user confirmation, wires, transfers, or removes them.
refactor-clean
You are a code refactoring expert specializing in clean code principles, SOLID design patterns, and modern software engineering best practices. Analyze and refactor the provided code to improve its quality, maintainability, and performance.