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 emilvaintrub/ShowRunner --skill pen-testgit clone --depth 1 https://github.com/emilvaintrub/ShowRunnerWrote 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/emilvaintrub/showrunner/pen-test)<a href="https://agentmods.dev/skills/emilvaintrub/showrunner/pen-test"><img src="https://agentmods.dev/badge/skills/emilvaintrub/showrunner/pen-test.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 | $0.00089 | $0.00894 |
| Opus 5 | $0.00044 | $0.00447 |
| Sonnet 5 | $0.00018 | $0.00179 |
| Haiku 4.5 | $0.00009 | $0.00089 |
Grade A, and why
pen-test 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 6d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pen Test
Run a bounded security assessment whose authorization, coverage, evidence, and cleanup can be audited. Treat penetration testing as one implementation technique inside Sentry, not as proof of complete security.
Load
- Read
../../core/method.md. - Read the active project's
.claude/showrunner/config.md. - Read
../method.md. - Read method.md.
- Read references/authorization.md before any active request.
- Read references/coverage.md while planning or reporting.
- Load only the applicable sections of references/profiles.md.
- Read references/validation.md before confirming findings.
- Load only the required asset template or schema.
Route
init: create a draft engagement, scope manifest, and Rules of Engagement; perform no target interaction.plan: inventory actors, entry points, assets, trust boundaries, and applicable versioned test cases; produce the coverage ledger.run: execute only approved tests at or below their authorized safety class.validate: independently challenge evidence, exploit preconditions, impact, and the PoC before confirming a finding.retest: execute the minimal approved reproduction against the remediated target and record closure or residual risk.report: assemble limitations, coverage, findings, retest state, and cleanup status; never translate coverage into a security guarantee.abort: stop target interaction, preserve minimal evidence, execute cleanup, and record the stop reason.ingest <report-path>: normalize external findings for Sentry triage without treating their severity or conclusions as authoritative.
Required Sequence
AUTH -> INVENTORY -> PLAN -> RUN -> VALIDATE -> REPORT -> RETEST -> CLEANUP
Do not skip a stage. A report may be issued before retest only when it states that remediation verification is pending.
What ships with it
19 files 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.
- agents/openai.yaml 204 B
- assets/cleanup.md 597 B
- assets/coverage-ledger.md 959 B
- assets/finding.md 806 B
- assets/report.md 1013 B
- assets/retest.md 412 B
- assets/rules-of-engagement.md 1.1 KB
- assets/scope-manifest.md 1.1 KB
- assets/test-plan.md 629 B
- method.md 5.5 KB
- references/authorization.md 2.3 KB
- references/coverage.md 2.2 KB
- references/profiles.md 2.8 KB
- references/validation.md 1.6 KB
- schemas/catalog.schema.json 996 B
- schemas/coverage.schema.json 2.0 KB
- schemas/engagement.schema.json 5.9 KB
- schemas/finding.schema.json 1.6 KB
- schemas/retest.schema.json 629 B
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.
- 6d ago First seen · 88 lines · 89 tokens per session scan A c8b3dd89e7c4
pen-test is a skill published in the GitHub repository emilvaintrub/ShowRunner (2 stars, last pushed 2mo ago), licensed MIT. It adds 89 tokens to every session and 894 once invoked, about $0.0004 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
kyzo-plan-write-story
Author or revise board story contracts (name, sources, condemned, ceiling, choice, allowlisted T#s, Final QA DoD). Not epic authorship (write-epic), not T# execution (run-story), not raw board moves (manage-board).
kyzo-plan-write-epic
Author or revise board epics — name + outcome as the value state the story group creates. Not story contracts (write-story), not T# runs (run-story), not column moves (manage-board).
kyzo-plan-run-story
Parent after startstory — arm paths, spawn demolition then each T#, run board Check, spawn judge, allowlist-commit on PASS / path-restore on FAIL, Final QA verdict then checkfinalqa. Not write-story or manage-board.
kyzo-plan-manage-board
ONLY board read/write — plan MCP tools, never raw gh. Tool descriptions are role×verb. Not write-story or run-story.
kyzo-plan-task-completion-request
Minimal completionrequest the development-task sends to the judge after allowlist edits. Not board writes, not git, not tree meters.
worker-integration
Worker-Agent integration for intelligent task dispatch and performance tracking.