Borrowing it
Nothing to install: this file belongs to cairn-framework/cairn. 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/cairn-framework/cairn/main/.claude/skills/cairn-loop-recovery/SKILL.mdgit clone --depth 1 https://github.com/cairn-framework/cairnWrote 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/cairn-framework/cairn/cairn-loop-recovery)<a href="https://agentmods.dev/skills/cairn-framework/cairn/cairn-loop-recovery"><img src="https://agentmods.dev/badge/skills/cairn-framework/cairn/cairn-loop-recovery/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/cairn-framework/cairn/cairn-loop-recovery"><img src="https://agentmods.dev/badge/skills/cairn-framework/cairn/cairn-loop-recovery.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 | $0.00071 | $0.01480 |
| Opus 5.5 | $0.00028 | $0.00592 |
| Sonnet 5.5 | $0.00014 | $0.00296 |
| Haiku 4.5 | $0.00007 | $0.00148 |
Grade A, and why
cairn-loop-recovery 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 2mo 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cairn-loop-recovery
Recover loop state for the preflight verdict loop mode's table selected. Loop mode owns the verdict table (state classification and the fail-closed backstops); this skill owns the procedure each recovery row expands into. Run the section matching the verdict and return the token it declares.
Exit tokens
This skill declares the mid-iteration tokens loop mode routes on. Return exactly one, as the final line, then let loop mode's flow continue:
RECOVERED- the state was recovered; continue the iteration at the phase the calling verdict names (Verify for in-place recovery, Scope for an adopted branch, or continue preflight after cleanup/quarantine-park).LOOP HALTED- the state is unclassifiable or unrecoverable by this skill (intent unclear, conflicting evidence, a violation the maintainer must judge). Touch nothing; report; halt.
Paths that finish the iteration (open-PR recovery after merge, quarantine
via a recover-todo) hand off to cairn-loop-landing; that skill emits
the terminal token (ITERATION COMPLETE or LOOP HALTED). This skill does
not re-emit a terminal token after a successful hand-off.
1. Dirty tree on a loop/* branch whose slug maps to a known unit
Finishing that unit IS this iteration. Recover in place:
- Read the full diff against the unit's intent (the todo body or finding
code):
git diff,git log origin/main..HEAD, and the unit's artefacts. - Decide coherence: complete the unfinished work, or trim incomplete work back to a single coherent landed unit. Prefer trimming over expanding when the diff has sprawled beyond one reviewable PR.
- Return
RECOVERED. Loop mode continues at Verify, then Land viacairn-loop-landing. Do not invoke landing from this skill.
Invariant (a fail-closed backstop, owned by loop mode): no checkout of
any kind until the tree is clean. If intent is unclear, do not guess; emit
LOOP HALTED.
2. Clean tree, exactly one open loop/* PR
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.
- 2mo ago First seen · 117 lines · 71 tokens per session scan A 9ae94ff37925
cairn-loop-recovery is a skill published in the GitHub repository cairn-framework/cairn (53 stars, last pushed yesterday), licensed Apache-2.0. It adds 71 tokens to every session and 1,480 once invoked, about $0.0003 per session on Opus 5.5. 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.
cairn-loop-recovery compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| cairn-loop-recoverycairn-framework/cairn | Skill | 53 | yesterday | Apache-2.0 | A | 71 | Claude Code |
| merge-batchdiegosouzapw/OmniRoute | Skill | 83k | 5d ago | MIT | A | 46 | Claude Code |
| prowler-commitprowler-cloud/prowler | Skill | 15k | yesterday | Apache-2.0 | A | 44 | Claude Code, Codex |
| gh-auth-isolationgithub/gh-aw | Skill | 5.6k | yesterday | MIT | A | 20 | Claude Code, Codex |
| github-skillzeenie-ai/OpenCompany | Skill | 1.1k | yesterday | MIT | A | 51 | Claude Code |
| comet-githubrpamis/comet | Skill | 3.3k | yesterday | MIT | A | 72 | Claude Code, Codex |
| release-helperSahir619/fable-method | Skill | 2.3k | 1mo ago | MIT | A | 43 | Claude Code |