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 yuri-semenenko/ai-engineering-workspace --skill security-passgit clone --depth 1 https://github.com/yuri-semenenko/ai-engineering-workspaceWrote 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/yuri-semenenko/ai-engineering-workspace/security-pass)<a href="https://agentmods.dev/skills/yuri-semenenko/ai-engineering-workspace/security-pass"><img src="https://agentmods.dev/badge/skills/yuri-semenenko/ai-engineering-workspace/security-pass.svg" alt="Measured on agentmods" 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 | $0.00104 | $0.01049 |
| Opus 5 | $0.00052 | $0.00524 |
| Sonnet 5 | $0.00021 | $0.00210 |
| Haiku 4.5 | $0.00010 | $0.00105 |
Grade A, and why
security-pass 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 7d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Pass
A staged security hardening workflow, distinct from a one-shot scan. The shape is: recon → numbered checklist → approval → atomic remediation commits, typecheck-gated per task. This matches the workflow the user validated in prior passes; follow it rather than diving straight into edits.
For a quick read-only scan of the current diff, use the built-in /security-review instead. This skill is for when there is real remediation work to plan and land safely.
Phase 1 — Recon (read-only)
- Map the attack surface relevant to the change or area: entry points (routes, handlers, server actions), trust boundaries, auth/authz checks, data flowing from untrusted input to sinks (DB, shell, HTML, file system, external calls), secret handling, and dependency surface.
- Fan out with
Exploresubagents per subsystem when the surface is broad — keep raw findings out of the main context, per the persona's session-hygiene rule. - Catalog candidate issues with category + severity. Do not fix anything yet.
Phase 2 — Numbered checklist (for approval)
Produce a single ordered checklist. Each item:
| # | Category | Severity | Location (file:line) |
Issue | Proposed fix | Effort |
|---|
- Severity by exploitability × blast radius. Order most-critical first.
- Each item must be independently committable — that is what makes the next phase atomic.
- Stop here and wait for approval. The user picks which items proceed (and may defer some, as in past passes where later-stage items were deferred behind a product milestone). Do not start remediation until the list is approved.
Phase 3 — Remediation (atomic, typecheck-gated)
For each approved item, in order:
- Implement the minimal fix for that one item. Do not bundle unrelated hardening into the same change.
- Typecheck gate: run the project's typecheck (and targeted tests if they exist) before committing. If it fails, fix before moving on — never commit a red tree.
- Commit the single item per the
commitskill rules (one logical change, noCo-Authored-By, ask before pushing). Reference the checklist item in the subject. - Move to the next item only after the current one is green and committed.
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.
- 7d ago First seen · 63 lines · 104 tokens per session scan A 0cc006ca1f58
security-pass is a skill published in the GitHub repository yuri-semenenko/ai-engineering-workspace (1 stars, last pushed 6d ago), licensed MIT. It adds 104 tokens to every session and 1,049 once invoked, about $0.0005 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
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
My Skill
Content here.
task-generation
Reference material with the canonical task-format grammar and decomposition rules for plan-to-tasks expansion. Loaded on demand by generate-tasks; not directly invokable.
implementation-standards
Reference material with coding standards (defensive coding, error handling, testing patterns). Loaded on demand by the Developer sub-agent (.github/agents/developer.md); not directly invokable.
spec-authoring
Reference material for writing product, technical, and operational specifications (work-item priorities, requirement families, success criteria). Loaded on demand by specify-feature; not directly invokable.
audit
Audits recent work against its Definition of Done and project patterns. Runs the test suite, compares code against the spec, and reports PASS / PARTIAL / FAIL. Also runs the Critical Gate — a safety scan of the diff for destructive or dangerous operations. Generates an incremental prompt pack for any gaps found. With…