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 naimkatiman/continuous-improvement --skill recovery-classificationgit clone --depth 1 https://github.com/naimkatiman/continuous-improvementWrote 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/naimkatiman/continuous-improvement/recovery-classification)<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>- 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 | $0.00085 | $0.01103 |
| Opus 5 | $0.00043 | $0.00551 |
| Sonnet 5 | $0.00017 | $0.00221 |
| Haiku 4.5 | $0.00009 | $0.00110 |
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.
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 |
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.
- 8d ago First seen · 75 lines · 85 tokens per session scan A 9e66e748bd08
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.
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.
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…
sglang-diffusion-benchmark-profile
Use when benchmarking denoise latency or profiling a diffusion bottleneck in SGLang.
smiles-validation
Strict SMILES validation, structural comparison, and modification verification. Catches invalid LLM-generated molecules.
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.
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…