Borrowing it
Nothing to install: this file belongs to campfirium/foliole. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/campfirium/foliole/dev/.agents/skills/foliole-hosted-quality-repair/SKILL.mdgit clone --depth 1 https://github.com/campfirium/folioleWrote 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/campfirium/foliole/foliole-hosted-quality-repair)<a href="https://agentmods.dev/skills/campfirium/foliole/foliole-hosted-quality-repair"><img src="https://agentmods.dev/badge/skills/campfirium/foliole/foliole-hosted-quality-repair/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/campfirium/foliole/foliole-hosted-quality-repair"><img src="https://agentmods.dev/badge/skills/campfirium/foliole/foliole-hosted-quality-repair.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00091 | $0.01204 |
| Opus 5 | $0.00046 | $0.00602 |
| Sonnet 5 | $0.00018 | $0.00241 |
| Haiku 4.5 | $0.00009 | $0.00120 |
Grade A, and why
foliole-hosted-quality-repair 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 5d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Foliole Hosted Quality Repair
Act as the single visible repair controller only for an independent dev T7 Hosted Quality run. A handoff is a locator, not failure or stage evidence.
Route Before Diagnosing
- Read the stable workflow path, run ID, branch, URL, and workspace from the task.
- If the run is
.github/workflows/t7-release.yml, has branchrelease, or belongs to a T7 nested/platform stage, do not accept repair ownership, edit code, commit, dispatch, or create another task. Route the run URL and first failed stage to the existing pinned release task. - Only an independent
.github/workflows/t7-hosted-quality.ymlrun ondevis in repair scope. - T5 and T6 are reusable stages inside both top-level T7 workflows, not independent repair streams. Report their failures as
runTier=T7, failedStage=T5orrunTier=T7, failedStage=T6. - Legacy candidate, platform, or assembly workflow names do not establish a separate T7 repair owner.
If the pinned release task cannot be identified, report repairState=waiting-for-release-owner and stop. Never create a replacement release task from this skill.
Establish The Source Of Truth
- Read the complete run with
gh run view <run-id> --repo <repository> --json jobs,conclusion,event,headBranch,headSha,displayTitle,url,workflowNameand fetch failed-step logs withgh run view <run-id> --repo <repository> --log-failed. - If read-only GitHub access requires approval, request only the exact read operation. Without it, set
repairState=waiting-for-read-approval; do not diagnose from locator fields. - Confirm the returned branch is
devand the workflow is the independent T7 Hosted Quality entry. Treat any mismatch as a routing failure. - Use the returned commit identity only to correlate the observed run with repository history. Do not make it a human dispatch or branch-control input.
- Inspect
git status, the named commit, and relevant history. Preserve unrelated dirty changes; never switch, reset, or overwrite the workspace to match the run. - Inspect every failed job before editing. Set
failedStage=T5only for failure in the nested admission chain; otherwise setfailedStage=T6. Do not guess when evidence is incomplete.
What ships with it
1 file 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.
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.
- 5d ago First seen · 58 lines · 91 tokens per session scan A cf1ecf31818e
foliole-hosted-quality-repair is a skill published in the GitHub repository campfirium/foliole (121 stars, last pushed yesterday), licensed Apache-2.0. It adds 91 tokens to every session and 1,204 once invoked, about $0.0005 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 2026-09-06.
Other skills, from other repositories
tt
Quality gate immediately after building: prove that what was just built actually works, while the context is still hot. Six steps: scope what changed, run live on real data, break it on purpose, show a counter or log proving it ran, root-cause any failure and re-run, then a verdict with evidence. Only a green verdict…
local-chatgpt-token-heal
Re-mint a ChatGPT bearer token when a nightly sync exits with a token-expired code: the session cookie lives for months and deterministically produces a fresh bearer, with no LLM and no browser. Triggers: "/chatgpt-token-heal", "chatgpt token dead", or the sync failing on that error.
tg-check
Self-test both Telegram rails on this machine, the MCP connector and the userbot library, with a deterministic zero-token detector plus a real in-session MCP probe, and print a per-rail verdict with the exact fix for whichever is down. Triggers: "/tg-check", "are both tg rails up", "check telegram channels".
mcore-create-issue
Investigate a failing GitHub Actions run or job and create a GitHub issue for the failure.
debug-task
Diagnose and fix moon tasks that are broken, misconfigured, or behaving unexpectedly. Use this skill when a moon task is failing, not running, skipped, hanging, producing stale or wrong output, cached when it shouldn't be, re-running every time when it should be cached, or when outputs are empty or missing after a…
operating-github-ci-fixer
Use when the user asks OpenSRE to fix failing GitHub CI, GitHub Actions checks, failing pull request checks, a broken PR branch, or CI on a named branch such as main.