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 Cody-W-Tucker/Cognitive-Assistant --skill failure-recoverygit clone --depth 1 https://github.com/Cody-W-Tucker/Cognitive-AssistantWrote 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/cody-w-tucker/cognitive-assistant/failure-recovery)<a href="https://agentmods.dev/skills/cody-w-tucker/cognitive-assistant/failure-recovery"><img src="https://agentmods.dev/badge/skills/cody-w-tucker/cognitive-assistant/failure-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/cody-w-tucker/cognitive-assistant/failure-recovery"><img src="https://agentmods.dev/badge/skills/cody-w-tucker/cognitive-assistant/failure-recovery.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 | $0.00070 | $0.02075 |
| Opus 5 | $0.00035 | $0.01038 |
| Sonnet 5 | $0.00014 | $0.00415 |
| Haiku 4.5 | $0.00007 | $0.00208 |
Grade A, and why
failure-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 12d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Failure Recovery
When To Use
Load this when work is non-trivial and at risk of one of these drifts:
- About to recommend, implement, or answer before you have actually looked
- Clean-sounding draft leaning on weak or absent source contact
- Abstraction, helpers, config options, defensive checks, or file splits piling up
- A fix being made without a named cause
- Search still gathering context after the core question is already answerable
- Output technically correct but hard for the real operator to read, edit, or act on
- Prior analytical attempt missed on scope, rigor, or framing
- Requirements changed but work continued on the old model
- Tool or system not doing what was believed
Do Not Use
- Asset, action, and output form already named and next move obvious — extended analysis reopens settled scope
- Early scouting where rough and "good enough" is fine because you are only reducing uncertainty
- Precision rules below bind tightly only when output must guide implementation, sales, a non-technical user, or a later agent
- Pure initial bounding with no drift yet —
scope-framing - Pure discovery/commitment line call with no repair needed —
boundary-handoff - Pure structural excess with clear job — may interrupt into
complexity-reductionafter stance is read
First: Read The Stance
The right repair depends on stage. Infer from the user's verbs and task shape:
| Signal | Stance | Premature move |
|---|---|---|
| look, decide, plan, explore, understand | orientation / fit | execution |
| rewrite, add, search, note, make, treat this like… | execution | another framework |
| object unclear | exploration — map type, dirs, build, tests, lint, style, rules, workflow; name operator before recommending | prescription |
| multiple viable paths | planning — fit to real user, local conventions, complexity budget, maintenance; move once an option clears filters | endless deliberation |
| observed ≠ intended | diagnosis — separate actual vs expected before touching anything | blind patch |
| artifact exists but doesn't carry the point | refinement — tighten copy, cut moving parts, sharpen pain-point fit | new architecture |
| answer already supported enough | stop | more exploration |
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.
- 12d ago First seen · 156 lines · 70 tokens per session scan A b98a2437f182
failure-recovery is a skill published in the GitHub repository Cody-W-Tucker/Cognitive-Assistant (11 stars, last pushed 25d ago), licensed Apache-2.0. It adds 70 tokens to every session and 2,075 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
health-check
Project Health Check Orchestrator: Runs a comprehensive project health assessment by invoking the architecture-reviewer, tech-debt-analyzer, and security-auditor agents in sequence. Produces a unified Project Health Dashboard with scores, trends, and a prioritized improvement roadmap. Use when the user wants a 'health…
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…