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 OutlineDriven/odin-claude-plugin --skill fail-recovergit clone --depth 1 https://github.com/OutlineDriven/odin-claude-pluginWrote 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/outlinedriven/odin-claude-plugin/fail-recover)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/fail-recover"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/fail-recover/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/outlinedriven/odin-claude-plugin/fail-recover"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/fail-recover.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 | $0.00033 | $0.00788 |
| Opus 5 | $0.00016 | $0.00394 |
| Sonnet 5 | $0.00007 | $0.00158 |
| Haiku 4.5 | $0.00003 | $0.00079 |
Grade A, and why
fail-recover 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 4d 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.
This is a copy
88% identical to fail-recover — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fail recover
Contract
| Field | Bound contract |
|---|---|
| Trigger | User needs to restore service from a specific known failure using a prescribed recovery operation. |
| Authority | Reversible local: writes only the named local target; rollback is undo via the recorded rollback path. No remote mutation. State and follow the rollback path before mutating. |
| Side effect | The single prescribed recovery operation applied to the local configuration target. No scope widening, no retry with a different action. |
| Done | The recovery operation is applied to the target artifact and the health signal confirms service restoration. |
Inputs
Required:
- The known failure symptom: the observable condition that identifies the failure (error message, metric threshold, health-check output).
- The prescribed recovery operation: the single bounded action to apply.
- The authority source for the prescription: where the recovery operation is documented (a runbook, an incident postmortem, a vendor advisory, a playbook entry). Named explicitly so the operation can be validated.
- The target configuration artifact: the local file, setting, or service the operation changes.
Optional:
- An explicit rollback path. If absent, derive and record one before any mutation.
- A health signal or verification mechanism: the command, endpoint, or metric that confirms restoration. If absent, ask the user to name one before applying the operation.
Procedure
- Verify the observed symptom matches the known failure. Compare the observed condition against the documented symptom. If they do not match, stop. Done when: the symptom matches the known failure, or the skill stops with the mismatch reported.
- Validate the prescribed recovery operation against the named authority source. Confirm the operation is the one documented for this failure and that it targets only the named local artifact. If the authority source does not prescribe this operation for this symptom, stop. Done when: the operation is validated as prescribed and scoped to the named target.
- Record the explicit rollback path that reverses the recovery operation. If the user did not supply one, derive it from the operation's inverse and record it before any mutation. Done when: the rollback path is recorded.
- Apply the recovery operation to the named local target only. Done when: the recovery operation is applied to the named target.
- Verify restoration using the specified health signal or verification mechanism. Run the health check, query the endpoint, or read the metric. Done when: the health signal confirms service restoration, or the check fails and rollback is triggered.
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.
- 4d ago First seen · 51 lines · 33 tokens per session scan A 197dd78b034c
fail-recover is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed yesterday), licensed Apache-2.0. It adds 33 tokens to every session and 788 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to fail-recover, differing in 4 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…