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 aneja5/forge-skills --skill debugging-and-recoverygit clone --depth 1 https://github.com/aneja5/forge-skillsWrote 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/aneja5/forge-skills/debugging-and-recovery)<a href="https://agentmods.dev/skills/aneja5/forge-skills/debugging-and-recovery"><img src="https://agentmods.dev/badge/skills/aneja5/forge-skills/debugging-and-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/aneja5/forge-skills/debugging-and-recovery"><img src="https://agentmods.dev/badge/skills/aneja5/forge-skills/debugging-and-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 | $0.00056 | $0.00805 |
| Opus 5 | $0.00028 | $0.00402 |
| Sonnet 5 | $0.00011 | $0.00161 |
| Haiku 4.5 | $0.00006 | $0.00081 |
Grade A, and why
debugging-and-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 6d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debugging and Recovery
Overview
Reproduce → localize → fix → guard. Never guess at root cause. The fix is not done until a regression test guards it. For bugs with GitHub issues, see triage-issue for the full investigation + issue creation flow.
When to Use
- Something broke or behaves unexpectedly
- A test is failing and the cause is not obvious
- A bug has been reported and needs diagnosis before a fix
- An error is ambiguous — multiple possible causes
When NOT to Use
- The fix is obvious and well-understood — just implement with
tdd - The bug is a missing feature, not broken behavior — use
spec-driven-development - You want to preemptively prevent bugs — use
code-review-and-quality
Common Rationalizations
| Thought | Reality |
|---|---|
| "I know what the bug is" | You think you do. Reproduce it first. |
| "I'll just try this fix and see" | Untested fixes introduce new bugs |
| "The root cause is obvious from the stack trace" | Stack traces show symptoms, not causes |
| "A unit test would be too hard to write for this" | Write an integration test — the behavior is observable |
| "The fix is one line, no test needed" | One-line bugs are re-introduced in one line |
Red Flags
- Fixing before reproducing — you might be fixing the wrong thing
- Fix that passes all tests but doesn't change observable behavior
- No regression test added — the bug will return
- Root cause described as "it just wasn't working" — not a cause
- Fix modifies more than what the bug report describes
Core Process
Step 1: Reproduce
Get the minimal reproduction: exact steps, inputs, environment. If you can't reproduce it, you don't understand it. Run the failing scenario manually or via test before writing any fix.
Step 2: Write a failing test
Before fixing:
RED: Write a test that reproduces the bug
→ The test must fail
→ If it passes, your reproduction is wrong
The test proves you understand the bug.
Step 3: Localize
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.
- 6d ago First seen · 93 lines · 56 tokens per session scan A a7cd104c6fc1
debugging-and-recovery is a skill published in the GitHub repository aneja5/forge-skills (3 stars, last pushed 3mo ago), licensed MIT. It adds 56 tokens to every session and 805 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 2026-09-03.
Other skills, from other repositories
verify
Verify Elixir/Phoenix changes — compile, format, and test in one loop. Use after implementation, before PRs, or after fixing bugs.
fix-bug
Run the Fix Validation pipeline to investigate, fix, and validate a bug. Ensures deterministic pipeline execution with IssueAnalyzer, FixWriter, TestWriter (conditional), TestAudit (conditional), and FixValidator stages.
run-smoke-tests
Run Playwright smoke tests, debug failures, and verify fixes. Use for smoke, e2e, Playwright, or pre-ship browser verification.
fec-validation-fix
A workflow for running a project's existing validation commands and fixing failures in linting, type checks, tests, builds, CI, or local scripts. Linting checks code rules, while type checks verify that TypeScript types are used consistently.
prove-checks
Prove a passing check was capable of failing before recording it as evidence. Use when a test, CI job, build-and-diff, smoke test or rehearsal comes back green and that green is about to be treated as proof - especially when the check depends on a setup mutation (a sed/awk rewrite, an env var, a secret, a fixture…
wiring
When building infrastructure components, ensure they're actually invoked in the execution path.