A software-security workflow for finding, assessing, fixing, and checking security weaknesses. It includes governed penetration testing and records accepted risks and past regressions.

Sweeping applications and other software for security issues, fixing individual findings, independently verifying them, and maintaining security posture.

It organizes security reviews and preserves risk decisions, while requiring code fixes to stop before they are merged into the main branch.

sentry — Skill for Claude Code and Codex by emilvaintrub/ShowRunner

Install

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.

Any agent

npx skills add emilvaintrub/ShowRunner --skill sentry

Clone the repo

git clone --depth 1 https://github.com/emilvaintrub/ShowRunner

Made for: Claude Code, Codex.

Or install showrunner, the plugin that ships this one along with the rest of its 7 skills.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/emilvaintrub/showrunner/sentry/github.svg)](https://agentmods.dev/skills/emilvaintrub/showrunner/sentry)

Your own site

<a href="https://agentmods.dev/skills/emilvaintrub/showrunner/sentry"><img src="https://agentmods.dev/badge/skills/emilvaintrub/showrunner/sentry/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/emilvaintrub/showrunner/sentry"><img src="https://agentmods.dev/badge/skills/emilvaintrub/showrunner/sentry.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 109 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 976 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00109	$0.00976
Opus 5.5	$0.00044	$0.00390
Sonnet 5.5	$0.00022	$0.00195
Haiku 4.5	$0.00011	$0.00098

Measured today against content hash 507c5798f955, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sentry 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 today.

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.

showrunner/sentry/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sentry

Find security weaknesses systematically, preserve human risk decisions, and stop every code fix before main.

Load

Read ../core/lifecycle.md and ../core/method.md.
Read the active project's .claude/showrunner/config.md and the state ledger it names in lifecycle.state_file (default .claude/showrunner/state.md).
Read method.md.
Load knowledge/catalog.md for sweeps.
Load knowledge/standards.md only for mapping or refresh.
Load ../core/dispatch.md for fix.
Load ../core/merge.md for verify or merge.
Load pen-test/SKILL.md for pen-test.
Load only the template required by the requested command.

Route

Sentry runs the lifecycle security stage for every initiative (method section 4), started by the conductor after verify records SHIP. Its other commands are read-only or open new initiatives:

init: infer security bindings, preserve shared and sibling config, and optionally create a project security document.
sweep <category|all>: perform a read-only categorical review, ingest any configured external live-site scanner evidence such as Code Quality Check, collect configured browser evidence such as Playwright traces and console or network observations, and reconcile findings with accepted-risk and regression memory.
fix <finding-id>: open the finding as a new initiative at intake; the fix then runs every lifecycle stage (method section 8).
verify <finding-id>: independently review the exact feature tip against the original finding and regression catalog.
accept <finding-id>: append an evidence-backed risk decision with owner, expiry, and revisit trigger.
deps: run configured dependency tools and classify direct, transitive, override, and accepted cases; inventory dependency licences against sentry.license_policy and flag copyleft or unknown licences for the owner.
pen-test init|plan|run|validate|retest|report|abort|ingest: route a governed assessment through the nested Pen Test skill.
pen-test <report-path>: compatibility alias for pen-test ingest <report-path>.
monthly: refresh knowledge, sweep, audit dependencies, age accepted risks, and write one digest without starting fixes. When enabled, the conductor reminds the owner at session start once it is overdue, and queues each confirmed finding as an initiative.
refresh-knowledge: fetch authoritative pins through the configured adapter, cache evidence, and flag drift.
merge: after exact-tip SHIP, required smoke, and explicit approval, reuse the shared two-commit ceremony.

Read the full file on GitHub · 83 lines

Files

What ships with it

35 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.

Changes

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.

today Changed · +1 lines 507c5798f955
1mo ago Changed · +9 lines 6f3621fafb22
2mo ago First seen · 73 lines · 109 tokens per session scan A 9b78966d685f

Subscribe to this mod's changes

sentry is a skill published in the GitHub repository emilvaintrub/ShowRunner (2 stars, last pushed yesterday), licensed MIT. It adds 109 tokens to every session and 976 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 2026-08-31.

Claude Code Security agentic-workflow ai-agents codex cursor

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation. Continuation mode: infer requirements, state assumptions, propose design in one message — no Q&A loop.

chadixearth/graphyloop · 58 tokens

ai-video-prompt-engineer

Use when the user wants to create AI video generation prompts for a brand, product, website, or topic. Includes interactive Q&A flow to gather requirements then outputs a single unified prompt (one paste) for tools like OmniFlash, Runway, Pika, Kling, Sora. Do NOT use for HyperFrames/Remotion video creation workflows.

chadixearth/graphyloop · 77 tokens

frontend-security

Use this skill when writing or reviewing client-side code that renders user data, stores tokens, calls an API, or embeds third-party scripts - React/Next/Vue/Svelte or plain DOM. Covers XSS sinks, token storage, environment-variable leakage, CSP and security headers, iframe and postMessage trust, and the checks that…

chadixearth/graphyloop · 80 tokens

api-contract-design

Use this skill when freezing the interface between a backend and its clients before parallel work starts, or when changing an endpoint other code already calls - request/response shapes, status codes, error envelope, pagination, filtering, idempotency, versioning, and the breaking-change rules. Covers writing the…

chadixearth/graphyloop · 79 tokens

dependency-audit

Use this skill before adding a dependency, when an audit or Dependabot alert fires, or when a lockfile changes in a review - triaging CVEs by real reachability, spotting typosquats and install scripts, pinning and lockfile discipline, and license checks. Covers deciding what actually needs fixing instead of chasing…

chadixearth/graphyloop · 74 tokens

graphyloop-waves

Use this skill when a request spans more than one layer (database + backend + frontend, or a feature plus a data pipeline). Turns the request into contract-first parallel waves with enforced dependencies, exclusive file ownership and per-lane acceptance checks, using the graphyloop planner and swarm.

chadixearth/graphyloop · 63 tokens