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 quay/ai-helpers --skill quay-retro-signal-filtergit clone --depth 1 https://github.com/quay/ai-helpersWrote 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/quay/ai-helpers/quay-retro-signal-filter)<a href="https://agentmods.dev/skills/quay/ai-helpers/quay-retro-signal-filter"><img src="https://agentmods.dev/badge/skills/quay/ai-helpers/quay-retro-signal-filter/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/quay/ai-helpers/quay-retro-signal-filter"><img src="https://agentmods.dev/badge/skills/quay/ai-helpers/quay-retro-signal-filter.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 | $0.00048 | $0.00685 |
| Opus 5 | $0.00024 | $0.00342 |
| Sonnet 5 | $0.00010 | $0.00137 |
| Haiku 4.5 | $0.00005 | $0.00068 |
Grade A, and why
quay-retro-signal-filter 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 7d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quay Retro Signal Filter
What this skill controls
This skill controls only proposal eligibility and deduplication for the retro
agent's proposals array. The built-in retro-analysis skill owns workflow
tracing, evidence gathering, existing-issue searches, localization, and the
required JSON output shape. Do not replace those procedures.
What this skill does not control
- The workflow reconstruction or investigation procedure.
- The required
summaryand proposal fields. - Existing-issue searches or duplicate-issue checks required by
retro-analysis. - The target repository decision or implementation of any fix.
Proposal eligibility
Before including a proposal, classify its primary evidence and impact.
Do not create a GitHub issue when the finding is exclusively about any of these:
- CodeRabbit path instructions or missed CodeRabbit review comments after merge.
- Agent-documentation completeness.
- An isolated review-comment or review-process lapse.
- Stylistic, naming, or other subjective preferences.
- One-off test cleanup.
- An item already marked duplicate, not planned, or superseded.
These observations may be mentioned briefly in summary when useful for the
retrospective record, but they must not become proposals.
A finding from one of those categories is proposal-eligible only when the evidence shows at least one concrete consequence:
- A production defect.
- A security exposure.
- A recurring CI failure.
- Repeated contributor failure across independent workflows or attempts.
A missed review comment is not itself a defect. Require evidence of one of the concrete consequences above; do not infer impact merely because a comment was unaddressed.
Root-cause deduplication
Treat proposals as belonging to the same root cause when they would be fixed by the same change, affect the same subsystem, or describe the same recurring failure mechanism. Before writing the final JSON:
- Group candidate findings by root cause or subsystem.
- Merge evidence and uncertainty into one proposal per group.
- Emit at most one proposal per root cause or subsystem.
- Put corroborating evidence for merged or filtered candidates in
summary, not in separate proposals. - Continue to apply
retro-analysis's mandatory search for overlapping open issues; do not file a new proposal when an existing issue covers the same improvement.
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.
- 7d ago First seen · 84 lines · 48 tokens per session scan A c1764fb9fc40
quay-retro-signal-filter is a skill published in the GitHub repository quay/ai-helpers (3 stars, last pushed 25d ago), licensed MIT. It adds 48 tokens to every session and 685 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 2026-09-04.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
magpie-security-issue-import-from-md
Open one or more tracking issues from a markdown file containing a batch of security findings. Each finding becomes one tracker landing in the Needs triage board column. The file itself is the full report — there is no inbound reporter to reply to and no PR to inspect.