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 stunt-double/stuntdouble-mcp --skill triage-feedbackgit clone --depth 1 https://github.com/stunt-double/stuntdouble-mcpWrote 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/stunt-double/stuntdouble-mcp/triage-feedback)<a href="https://agentmods.dev/skills/stunt-double/stuntdouble-mcp/triage-feedback"><img src="https://agentmods.dev/badge/skills/stunt-double/stuntdouble-mcp/triage-feedback/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/stunt-double/stuntdouble-mcp/triage-feedback"><img src="https://agentmods.dev/badge/skills/stunt-double/stuntdouble-mcp/triage-feedback.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00018 | $0.00658 |
| Opus 5 | $0.00009 | $0.00329 |
| Sonnet 5 | $0.00004 | $0.00132 |
| Haiku 4.5 | $0.00002 | $0.00066 |
Grade A, and why
triage-feedback 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 9d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Triage feedback
When to use
- During weekly feedback review sessions
- After a deployment to check for new issues surfaced by actors
- When prioritizing UX improvements for the next sprint
- When closing the loop on fixed issues
Instructions
-
Pull untriaged feedback:
list_feedback(project_id, status: "new")→ get all new feedback items
-
Review each item in detail:
get_feedback(feedback_id)→ read full details including actor context, screenshots, and evidence
-
Assess each item:
- Is it valid? — Real UX issue vs expected behavior or test artifact
- How severe? — Blocker (can't proceed), Major (significant friction), Minor (annoyance), Cosmetic (polish)
- Who's affected? — One persona type or multiple
- Is it new? — First occurrence or repeat of a known issue
-
Update status:
update_feedback_status(feedback_id, status: "reviewed")→ triaged and needs actionupdate_feedback_status(feedback_id, status: "resolved")→ issue has been fixedupdate_feedback_status(feedback_id, status: "dismissed")→ false positive or not actionable
-
Cross-reference for patterns:
list_actors(workspace_id)→ check which personas are most affectedlist_workflows(workspace_id)→ identify workflows that cover the affected areas- Look for clusters: multiple feedback items about the same flow, same actor type, or same area
-
Summarize findings:
- Total items reviewed, by status
- Top patterns or clusters
- Recommended actions (new workflows, actor updates, code fixes)
Example output
Feedback Triage — March 28, 2026
Reviewed: 7 new items
Triaged:
[reviewed] FB-301: Search returns empty for partial queries (Major, Power User)
[reviewed] FB-302: Modal not keyboard-dismissable (Major, Accessibility User)
[reviewed] FB-303: Onboarding tooltip overlaps CTA button (Minor, New User)
[dismissed] FB-304: Duplicate of FB-298
[reviewed] FB-305: Slow load on settings page (Major, Mobile User)
[dismissed] FB-306: Expected behavior — empty state on fresh account
[reviewed] FB-307: Confusing label on export button (Minor, Enterprise Admin)
Patterns:
- 2 accessibility items this week (up from 0 last week) — consider an a11y checklist
- Search issues recurring — needs a dedicated search workflow
Actions:
1. Fix FB-302 keyboard trap before next release
2. Create "Keyboard Navigation" checklist
3. Add search-specific workflow with varied query patterns
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.
- 9d ago First seen · 69 lines · 18 tokens per session scan A d6dff2849684
triage-feedback is a skill published in the GitHub repository stunt-double/stuntdouble-mcp (1 stars, last pushed 24d ago), licensed MIT. It adds 18 tokens to every session and 658 once invoked, about $0.0001 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
parallel-feature-development
Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…
bazel-build-optimization
Optimize Bazel builds for large-scale monorepos. Use when configuring Bazel, implementing remote execution, or optimizing build performance for enterprise codebases.
track-management
Use this skill when creating, managing, or working with Conductor tracks - the logical work units for features, bugs, and refactors. Applies to spec.md, plan.md, and track lifecycle operations.
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.
contact-cache
Track all identified/contacted people across strategies. CSV-backed contact database with dedup by LinkedIn URL or email. Prevents duplicate outreach when running strategies on a recurring cadence.
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.