recovery-classification

recovery-classification is a skill for Claude Code from naimkatiman/continuous-improvement. It costs 85 tokens per session (1,103 once invoked), scanned A, original, MIT.

A failure-handling skill that labels a problem—such as a provider, tool-schema, policy, Git, worktree, or runtime failure—before deciding what to do next.

In plain words
What is it for?
Use it after a failed verification step, automated loop, or rejected tool call to choose whether to retry, repair, pause, or stop.
Why use it?
It prevents blindly retrying errors that will keep failing for the same reason.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Part of the continuous-improvement plugin — 27 skills, 6 hooks shipped together

Good fit Use it after a failed verification step, automated loop, or rejected tool call to choose whether to retry, repair, pause, or stop.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/naimkatiman/continuous-improvement/recovery-classification
Install

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.

Any agent
npx skills add naimkatiman/continuous-improvement --skill recovery-classification
Clone the repo
git clone --depth 1 https://github.com/naimkatiman/continuous-improvement

Made for: Claude Code.

Or install continuous-improvement, the plugin that ships this one along with the rest of its 27 skills, 6 hooks.

Wrote 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.

agentmods badge for recovery-classification

README.md
[![agentmods](https://agentmods.dev/badge/skills/naimkatiman/continuous-improvement/recovery-classification.svg)](https://agentmods.dev/skills/naimkatiman/continuous-improvement/recovery-classification)
Your own site
<a href="https://agentmods.dev/skills/naimkatiman/continuous-improvement/recovery-classification"><img src="https://agentmods.dev/badge/skills/naimkatiman/continuous-improvement/recovery-classification.svg" alt="Measured on agentmods" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,103 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00085 $0.01103
Opus 5 $0.00043 $0.00551
Sonnet 5 $0.00017 $0.00221
Haiku 4.5 $0.00009 $0.00110

Measured 8d ago against content hash 9e66e748bd08, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

recovery-classification 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 8d 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.

plugins/continuous-improvement/skills/recovery-classification/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Recovery Classification Skill

When a phase or unit fails, name the failure class first. Generic "retry on failure" hides repeatable failure modes and turns them into flaky tests.

When to Use

  • After any Phase 1–6 failure in verification-loop.
  • After any auto-loop unit that exits non-zero.
  • After any tool call the harness rejects (schema validation, policy gate, deterministic block).
  • Before re-running anything that just failed — classification fires once, before the first retry.

Why This Skill Exists

GSD-2's CONTEXT.md names "Recovery Classification" as one of four runtime invariant modules. Common failure modes it catches:

  • Deterministic-policy blocks misclassified as generic provider failures — gateguard denials retried in a loop until budget is exhausted.
  • Schema-validation failures retried verbatim — wasting tokens on a call the validator will keep rejecting.
  • Stale-worker / stale-lock states — no retry can resolve a worker that died holding a lock; the loop just spins.
  • Worktree-invalidity errors — recovery can't fix without operator intervention; retrying writes to a broken root.

A retry without a class is a guess; a guess at scale is a budget leak.

The Classification Taxonomy

Six classes. Each maps to one intentional action:

Class Signal Action
provider API timeout, 5xx, rate limit, network, transient cloud error retry with exponential backoff
tool-schema tool input rejected by validator, missing required field, type mismatch repair input, do not retry verbatim
deterministic-policy gateguard / write-gate / permission denied / explicit policy block pause, ask operator (do not retry)
git merge conflict, detached HEAD, unmerged paths, lockfile, pre-commit hook self-heal if known recipe, else pause
worktree missing .git, invalid root, lease lost, prunable worktree, foreign session stop — never spawn workers into unresolved paths
runtime OOM, segfault, host kill, parent process gone, context exhaustion stop, surface to operator

Read the full file on GitHub · 75 lines

Changes

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.

  1. 8d ago First seen · 75 lines · 85 tokens per session scan A 9e66e748bd08

Subscribe to this mod's changes

recovery-classification is a skill published in the GitHub repository naimkatiman/continuous-improvement (7 stars, last pushed yesterday), licensed MIT. It adds 85 tokens to every session and 1,103 once invoked, about $0.0004 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 2026-08-31.

Related

Other skills, from other repositories

ml-debug

Use when something is failing in ML/AI work — OOM, NaN, divergence, crashes, bad throughput, wrong outputs, dependency conflicts.

Leeroo-AI/superml · 32 tokens

agent-pitbook

Search and contribute to Agent Pitbook, a structured debugging pit knowledge base for coding agents. Use when Codex is diagnosing recurring local-development failures, sandbox issues, dependency installation errors, Docker or port problems, MCP/tool quirks, browser automation failures, or when a verified debugging…

laozhangzzz/agent-pitbook · 70 tokens

sglang-diffusion-benchmark-profile

Use when benchmarking denoise latency or profiling a diffusion bottleneck in SGLang.

sgl-project/sglang · 26 tokens

smiles-validation

Strict SMILES validation, structural comparison, and modification verification. Catches invalid LLM-generated molecules.

synthetic-sciences/openscience · 24 tokens

binary-triage

Performs initial binary triage by surveying memory layout, strings, imports/exports, and functions to quickly understand what a binary does and identify suspicious behavior. Use when first examining a binary, when user asks to triage/survey/analyze a program, or wants an overview before deeper reverse engineering.

cyberkaida/reverse-engineering-assistant · 65 tokens

quota-debug

Diagnose Kubernetes native ResourceQuota and LimitRange admission rejections (exceeded quota, forbidden by LimitRange, FailedCreate). Checks namespace quotas, current usage, LimitRange constraints, and ReplicaSet events to identify why pods cannot be created. Not applicable to Volcano Queue — use…

scitix/siclaw · 69 tokens