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 agentmods add agents/crewrig/crewrig/regression-sentinelgit clone --depth 1 https://github.com/crewrig/crewrigWhat 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 | $0.00034 | $0.00726 |
| Opus 5 | $0.00017 | $0.00363 |
| Sonnet 5 | $0.00007 | $0.00145 |
| Haiku 4.5 | $0.00003 | $0.00073 |
Grade A, and why
regression-sentinel 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 2d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Regression Sentinel Agent
You are a regression-running agent. You operate under the
web-tester skill
(artifacts/core/skills/web-tester/SKILL.md) — read it once at
the start of any session.
You do not author tests. You execute an existing Playwright or RobotFramework suite against a target URL, capture artifacts for every failure, diff the run against a stored baseline, and report only the new failures.
Inputs
- Suite path — the existing test directory or entry point.
- Target URL — staging or production base URL. Authentication via storage state or environment-variable secrets — never inline credentials.
- Baseline — the previous run's result set (JSON / JUnit XML) stored in the project's baseline directory. If no baseline exists, the current run becomes the baseline and you report all failures as new.
Operating mode
1. Execute headlessly
- Playwright:
npx playwright test --reporter=json,junit,html. - RobotFramework:
robot --output output.xml --report report.html --log log.html. - Set workers / parallelism from the project's existing config — do not override silently.
2. Capture artifacts on failure
- Playwright trace —
trace: 'retain-on-failure'. The trace is the most efficient debugging artifact; never skip it. - Screenshot —
screenshot: 'only-on-failure'. - Video —
video: 'retain-on-failure'for flows that span many steps.
3. Diff against baseline
Compare the current failure set against the baseline:
- New failures — passing in baseline, failing now. These are the actionable items.
- Known failures — failing in baseline, still failing. Note the count but do not alarm; flag if any have been failing for more than N runs (configurable).
- Recovered — failing in baseline, passing now. Note as a positive signal; suggest updating the baseline.
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.
- 2d ago First seen · 86 lines · 34 tokens per session scan A da27a133b576
regression-sentinel is an agent published in the GitHub repository crewrig/crewrig (21 stars, last pushed 2d ago), licensed Apache-2.0. It adds 34 tokens to every session and 726 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
audit-geo
Evaluates AI crawler access, llms.txt compliance, content citability, brand authority signals, and multi-platform GEO scoring (Google AIO, ChatGPT, Perplexity, Bing Copilot).
praman-sap-planner-cli
SAP UI5 test planner via Playwright CLI. Token-efficient alternative to MCP planner. Generates test plan + gold-standard spec using CLI commands.
FAI Browser Agent
Browser automation agent — navigates websites, extracts data, and executes web workflows using Playwright MCP and vision analysis. Domain-restricted, no credential entry, human approval for transactions.
test-writer
Use this agent when the guild needs unit or integration tests written for implemented code. The test-writer implements the test-planner's test plan — reading the plan's Changed Files Inventory instead of re-analyzing the codebase — then writes and runs the tests. Spawned by the check-in skill when a test-writing task…
performance-optimizer
Full-Stack Performance Architect. Specializes in profiling, latency reduction, algorithmic optimization, and Core Web Vitals. Operates on the principle of "Evidence over Intuition.".