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 telus-labs/stagecraft --skill auditgit clone --depth 1 https://github.com/telus-labs/stagecraftWrote 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/telus-labs/stagecraft/audit)<a href="https://agentmods.dev/skills/telus-labs/stagecraft/audit"><img src="https://agentmods.dev/badge/skills/telus-labs/stagecraft/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/telus-labs/stagecraft/audit"><img src="https://agentmods.dev/badge/skills/telus-labs/stagecraft/audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00103 | $0.06490 |
| Opus 5.5 | $0.00041 | $0.02596 |
| Sonnet 5.5 | $0.00021 | $0.01298 |
| Haiku 4.5 | $0.00010 | $0.00649 |
Grade A, and why
audit scanned grade A with 1 finding 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 2mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Direct evidence only:** `verified_by` must name what was checked. Good examples: `rg -n "functionName" src/`, `node --test tests/foo.test.js`, `curl ... returned 403`, or `read src/auth.js:42-91 and traced caller in How it starts
The opening of the file, as written. The whole thing — 467 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit a Codebase
A four-phase analysis pass over an existing codebase. Different from Stagecraft's 18-stage pipeline — the pipeline builds features through staged production; an audit is read-only analysis of code that already exists. The output is a prioritized roadmap, not a deployable change.
When to use this vs the pipeline
- Audit: "I want to understand this codebase and find what to fix." Read-only. Produces
docs/audit/00-project-context.mdthroughdocs/audit/10-roadmap.md. Use before joining a project, before a refactor, before a security review, or as a periodic health check. - Pipeline (
devteam stage <name>): "I want to ship a feature through structured production." Writes code. Produces gate JSON and artifacts underpipeline/. Use for any change with acceptance criteria.
If the user asks to "fix things found in the audit", that's the implement skill against docs/audit/10-roadmap.md items — not this skill.
Two entry points
/audit— full audit, Phases 0 through 3. Produces 11 output files. ~30–60 minutes wall-clock on a medium codebase. Includes human checkpoints between phases so you can correct course before deep analysis./audit-quick— Phases 0–1 only. Produces 6 output files (no security / performance / code-quality / roadmap). ~5–15 minutes wall-clock. Good for fast onboarding or pre-review orientation. The user can run/audit --resumelater to complete the deep analysis.
Both commands read this file and execute the phases below.
Inputs
- The target codebase you're auditing (the user's project, not the Stagecraft framework).
- Optional scope constraint:
/audit src/backend/focuses on one subtree. - Optional
<target-project>/docs/audit-extensions.md— project-specific checks appended to each phase. Read once per phase if present. Operators create this in the projects they audit; it does not live in the Stagecraft repo. - Optional
docs/audit/status.json— for--resume, names the last completed phase.
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.
- 2mo ago First seen · 467 lines · 103 tokens per session scan A 44353b01ed38
audit is a skill published in the GitHub repository telus-labs/stagecraft (7 stars, last pushed 1mo ago), licensed MIT. It adds 103 tokens to every session and 6,490 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
codeck
Keep Codex as the host. Use Codeck when the user explicitly asks to call Agy/AGY, Antigravity, Gemini, Claude, Kimi, Grok, Codeck, or another configured external executor. These names mean external Codeck executors, never internal Codex subagents. Build a compact task-specific brief, call that specialist, and return…
code-review
Perform thorough code review and audit of implemented features. Compares implementation against the technical plan, checks for AI-specific risks, and provides actionable feedback. Activate for: review, audit, code quality assessment, security review.
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
find-simplifications
Use for a periodic repo-wide sweep of qwen-code for accumulated excess surface — dead components and files, orphaned locale keys, exports nothing consumes, added-then-removed scaffolding — filing candidates on a tracking issue and landing only what a maintainer has said yes to. Repo-wide and evidence-first; every…
gitnexus
A code-graph analysis add-on for examining an existing codebase, including symbols, call paths, execution flows, and effects across repositories. It can query GitNexus through its command-line or MCP interfaces.
swarm-pr-review
Run a graph-guided, tool-augmented PR review using context packing, parallel exploration, mandatory repository-agnostic risk-family coverage with dispatch scaled to diff size and risk, independent reviewer validation, critic challenge, and metrics writeback. Use for deep pull request review with low false-positive…