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 mhmdreza-rafiei/agent-tools --skill recovergit clone --depth 1 https://github.com/mhmdreza-rafiei/agent-toolsWrote 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/mhmdreza-rafiei/agent-tools/recover)<a href="https://agentmods.dev/skills/mhmdreza-rafiei/agent-tools/recover"><img src="https://agentmods.dev/badge/skills/mhmdreza-rafiei/agent-tools/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/mhmdreza-rafiei/agent-tools/recover"><img src="https://agentmods.dev/badge/skills/mhmdreza-rafiei/agent-tools/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 | $0.00120 | $0.00895 |
| Opus 5 | $0.00060 | $0.00447 |
| Sonnet 5 | $0.00024 | $0.00179 |
| Haiku 4.5 | $0.00012 | $0.00089 |
Grade A, and why
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 9d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Not every problem is a bug. Not every bug needs debugging.
When something goes wrong, the instinct is to keep prompting — describe, fix, get another broken version, repeat. The session lengthens, the context pollutes, the code gets worse. The real problem is not knowing what type of failure you're dealing with. Diagnose the failure first, then prescribe the response. Two steps, never swapped.
Automation mode (default)
Infer the failure from the actual error, recent changes, and the context system rather than asking the developer to describe it. Read context/memory/progress.md (what state were we in?), context/plan.md (what was intended?), context/architecture.md (the boundaries). Only ask the developer when the cause is genuinely unknowable from what's in front of you.
Step 1 — Gather (without interrogating)
What was expected vs. what happened, and how many fix attempts have already been made (attempt count signals a fresh bug vs. a session that's gone wrong). Pull this from the conversation/logs/groundwork first; ask only for what you truly can't infer.
Step 2 — Identify the failure mode
Mode 1 — A specific thing is broken. Isolated (one component/function/route), the rest works, first or second attempt, the error is clear → normal bug with a findable root cause → targeted fix (3A).
Mode 2 — The session has gone wrong. Multiple attempts made it worse, fixes patching fixes, context full of failed tries, original problem unclear → polluted session → hard reset (3B).
Mode 3 — The foundation is wrong. Runs but is fundamentally wrong; built confidently on a misunderstood requirement/API/pattern → not a debugging problem → rethink (3C).
State which mode and why in one line, then act.
Step 3A — Targeted fix
Diagnose before touching code. Find the root cause, not the symptom (Root cause: … This differs from the symptom because …), then a precise fix that addresses it (no workaround). Apply it (in automation), or confirm first (interactive). If it doesn't work, stop — don't stack another fix; re-diagnose. Two wrong root-cause guesses → this is probably Mode 2 or 3.
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.
- 9d ago First seen · 54 lines · 120 tokens per session scan A 83fdcdb14b83
recover is a skill published in the GitHub repository mhmdreza-rafiei/agent-tools (5 stars, last pushed 25d ago), licensed MIT. It adds 120 tokens to every session and 895 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
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…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.