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 minghinmatthewlam/agent-guards --skill learn-from-mistakegit clone --depth 1 https://github.com/minghinmatthewlam/agent-guardsWrote 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/minghinmatthewlam/agent-guards/learn-from-mistake)<a href="https://agentmods.dev/skills/minghinmatthewlam/agent-guards/learn-from-mistake"><img src="https://agentmods.dev/badge/skills/minghinmatthewlam/agent-guards/learn-from-mistake.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 | $0.00059 | $0.00392 |
| Opus 5 | $0.00030 | $0.00196 |
| Sonnet 5 | $0.00012 | $0.00078 |
| Haiku 4.5 | $0.00006 | $0.00039 |
Grade A, and why
learn-from-mistake 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 3d 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.
What it actually says
Learn From Mistake
Fix the immediate result and the system that made the mistake easy.
Diagnose
Preserve the original request, wrong result, available context and tools, and the observation that exposed the failure. Inspect the real source and output. Treat the agent's explanation as a hypothesis, not proof.
Find the owning cause:
- Repository: Misleading structure, duplicate paths, weak types, or missing deterministic checks. Use
repo-setupto choose and prove the strongest proportional prevention. - Verification: The wrong surface was checked, proof was weak, or the feature was not covered. Use
create-verification-skillormaintain-verification-skill. - Task boundary: Required context, access, ownership, or tools were missing or unclear. Fix that boundary.
- Judgment: The setup was adequate and recurrence is unlikely. Correct the result without adding machinery.
Prevent And Retry
Implement the prevention within the authorized scope. Prove it catches the same class of failure, then retry the original task and verify the affected surface.
Ask before changing global guidance, external state, or anything outside the task's write scope.
Report
Use concisely. State what failed, the verified cause, what changed to prevent recurrence, the corrected result, and remaining risk.
Gotchas
- Do not turn every ordinary bug into an agent rule.
- Do not add prose when code or tooling can enforce the behavior.
- Do not fix the visible symptom while leaving the demonstrated failure path open.
- Do not claim prevention worked without reproducing the relevant failure safely.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago Changed · -26 lines · -31 tokens per session 47befebfcca2
- 8d ago First seen · 63 lines · 90 tokens per session scan A 8ce95ff9c284
learn-from-mistake is a skill published in the GitHub repository minghinmatthewlam/agent-guards (40 stars, last pushed 6d ago), licensed MIT. It adds 59 tokens to every session and 392 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
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.