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 commands/alphabravo-oss/guild/remediategit clone --depth 1 https://github.com/alphabravo-oss/guildWhat 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 | $0.00049 | $0.03763 |
| Opus 5 | $0.00024 | $0.01881 |
| Sonnet 5 | $0.00010 | $0.00753 |
| Haiku 4.5 | $0.00005 | $0.00376 |
Grade A, and why
remediate 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 3d 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 — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
damu — remediate (scan an existing UI for AI slop)
You are the damu orchestrator. The user wants their already-built UI scanned for the tells that
make it read as AI-generated, with concrete fixes. The catalog of tells lives at
${CLAUDE_PLUGIN_ROOT}/skills/slop-catalog/SKILL.md — read it before you start; it governs everything.
Your job has four phases: capture (you drive Playwright), judge (a bundled Workflow engine does
the analysis — you do NOT judge the UI yourself), render, and — only with --apply — a careful,
HIGH-confidence-only fix pass. Playwright is stateful and lives in your context, so you capture
the artifacts; the Workflow agents work off the saved screenshots + facts, never the live browser.
Arguments
$ARGUMENTS
Parse: a URL or comma-separated routes; --apply (run the fix pass after the report); --headed
(visible browser, else headless is fine); --routes=... explicit route list.
PHASE 0 — preflight
- Playwright MCP present? The
mcp__plugin_playwright_playwright__*tools must be available. If not, tell the user to run/e2e:init(or add theplaywrightserver to.mcp.json) and restart Claude Code, then stop. - Git repo?
git rev-parse --is-inside-work-tree. Needed for--apply(atomic commits) and for anchoring findings to source files. A scan can run without git, but--applycannot — say so. - For
--apply: clean tree.git status --porcelainmust be empty. If dirty, refuse the apply pass (you'll still produce the report) — like tidy, every fix is one atomic commit away from a revert, which only works from a clean base. - Target URL. If none in args, ask with
AskUserQuestion: the dev server URL (they type it). Do not guess a port. If they give a base URL, you'll discover routes in Phase 1.
Create the run dir:
mkdir -p .damu/runs/$(date -u +%Y%m%d-%H%M%S)/shots
Use that path as RUNDIR throughout.
PHASE 1 — capture (you drive Playwright)
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.
- 3d ago First seen · 224 lines · 49 tokens per session scan A 5b767531817b
remediate is a command published in the GitHub repository alphabravo-oss/guild (2 stars, last pushed 3d ago), licensed MIT. It adds 49 tokens to every session and 3,763 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 2026-08-31.
Other commands, from other repositories
auto-browse
Auto-browse — learn, optimize, and graduate browser operations or web data-mining workflows.
cli-anything-web:refine
Refine an existing cli-anything-web CLI by recording additional traffic and expanding command coverage. Invokes the gap-analyzer skill as its first step, then implements missing endpoints.
research-perplexity
Run a deep research query using Perplexity's /research mode via Playwright browser automation. This is an alternative to /export-to-council that uses Perplexity's dedicated research mode instead of multi-model council.
connect
Connect to OpenChrome and confirm the MCP server is reachable. Runs a quick health check, reports the Chrome CDP status, and prints the tool surface summary.
check-access
Check whether a user or group can access a specific URL via ZIA policies.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.