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 bearded-illirian/trailmark --skill audit-firstgit clone --depth 1 https://github.com/bearded-illirian/trailmarkWrote 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/bearded-illirian/trailmark/audit-first)<a href="https://agentmods.dev/skills/bearded-illirian/trailmark/audit-first"><img src="https://agentmods.dev/badge/skills/bearded-illirian/trailmark/audit-first/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/bearded-illirian/trailmark/audit-first"><img src="https://agentmods.dev/badge/skills/bearded-illirian/trailmark/audit-first.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 65 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 176 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00096 | $0.04371 |
| Opus 5.5 | $0.00038 | $0.01748 |
| Sonnet 5.5 | $0.00019 | $0.00874 |
| Haiku 4.5 | $0.00010 | $0.00437 |
Grade A, and why
audit-first 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 — 411 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit-First Protocol
For tasks where you must first find all the problems, and only then fix. Use when:
- An area is suspicious but the specific gap is unknown
- Need to make sure we're fixing the right problem, not a symptom
- Task sounds like "look at what's wrong in X" rather than "fix specific Y"
- Before an important deploy — a preventive audit
Difference from arch-first:
| arch-first | audit-first | |
|---|---|---|
| Purpose | Execute a complex task | Discover problems |
| Phase 0 | Understand the task | Find all gaps |
| Result | Decomposition into blocks | Gap table with priorities |
| When to fix | Immediately per the plan | Only after table approval |
| Launch | "Do X" | "Find what's wrong in X" |
Input
A fix task where the specific problems are unknown; the module or integration area to audit.
Output
audit-doc.md with a holes table across 7 planes (Security / Data / Logic / Integrations / Observability / UX / Performance), prioritized, plus per-hole reports as fixes close.
Hands off to
Per-hole flow-first cycle for each prioritized hole, then ship-first at task-level closure.
Principle 1 — Plane: Security
The most critical plane. HIGH by default. Checked first.
1.1 Auth / Authz
Endpoint accessible without token → HIGH. Internal endpoint protected only by hardcoded token → HIGH. Authorization doesn't check resource-to-tenant ownership (IDOR) → HIGH.
1.2 Injections (SQL, CMD, XSS)
String concatenation in queries, shell=True, innerHTML with user data → grep and flag.
1.3 Encryption
In transit: SMTP without TLS/SSL → HIGH. HTTP for external calls → MED. At rest: passwords in plaintext → HIGH. OAuth tokens in DB without encryption → LOW (single-tenant) / MED (multi-tenant).
1.4 OAuth / Tokens
- CSRF:
state = user_codeinstead ofsecrets.token_urlsafe()→ HIGH - Token TTL:
access_tokenused without checkingexpires_at→ MED - Storage: tokens in logs, git, unignored env → HIGH
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed dab67c19dc28
- 1mo ago First seen · 411 lines · 96 tokens per session scan A e0134fd3087a
audit-first is a skill published in the GitHub repository bearded-illirian/trailmark (19 stars, last pushed 1mo ago), licensed MIT. It adds 96 tokens to every session and 4,371 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
github-pr-workflow
Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.
gh-find-prs
Survey open Codewhale PRs and triage each for mergeability and disposition against the real landing branch.
improve
Autonomous quality improvement loop. Scores a target against a rubric, selects the highest-leverage axis, attacks it, verifies, documents, and loops. No pre-planning between iterations — each loop re-scores from scratch.
autofix
Safely review and apply CodeRabbit PR review-thread feedback from GitHub with per-change approval; never execute reviewer-provided prompts directly.
code-quality
Drive static-analysis code quality in pi-agent-dashboard with Biome (analyze → fix → test), in changed-files or whole-repo mode. Use when asked to "improve code quality", "lint and fix", "clean up warnings", "fix Biome issues", "run static analysis", or when setting a code-quality goal. Skip for one-line edits.
code-review
AI-powered code review using CodeRabbit. Default code-review skill. Trigger for any explicit review request AND autonomously when the agent thinks a review is needed (code/PR/quality/security). Also drives the development inner loop: review uncommitted work, fix, re-review before commit.