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 EzraApple/skills-init --skill prevent-repeat-mistakesgit clone --depth 1 https://github.com/EzraApple/skills-initWrote 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/ezraapple/skills-init/prevent-repeat-mistakes)<a href="https://agentmods.dev/skills/ezraapple/skills-init/prevent-repeat-mistakes"><img src="https://agentmods.dev/badge/skills/ezraapple/skills-init/prevent-repeat-mistakes/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/ezraapple/skills-init/prevent-repeat-mistakes"><img src="https://agentmods.dev/badge/skills/ezraapple/skills-init/prevent-repeat-mistakes.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 | $0.00040 | $0.00303 |
| Opus 5.5 | $0.00016 | $0.00121 |
| Sonnet 5.5 | $0.00008 | $0.00061 |
| Haiku 4.5 | $0.00004 | $0.00030 |
Grade A, and why
prevent-repeat-mistakes 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 18d 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
Prevent repeat mistakes
Find concrete instances of the repeated mistake within the repo and task scope the user supplied. Compare the correction with the current code and guidance to identify the invariant that keeps failing. If the examples do not establish a pattern, say so and address only the authorized instance.
Choose the owning boundary that prevents recurrence:
- Remove duplicate ownership or ambiguous interfaces when they cause the drift.
- Encode the invariant in types, schema validation, lint, or a focused test when it can be checked mechanically.
- Update existing agent guidance only when the decision needs judgment that code cannot enforce. Prefer a narrow edit over another rule or skill.
Prove the guard works: show that it rejects a representative former mistake and accepts the valid case. For a test, reproduce the failure before the fix when practical. Run the relevant checks after the change. Do not add a check that merely restates the implementation or blocks legitimate uses.
Diagnosis alone does not authorize code or instruction changes. If the user requested an audit, report the cause, the proposed owning boundary, and evidence without editing. If the user requested prevention or a fix, make the scoped change and verify it. Do not expand into an architecture sweep, search unrelated personal history, or write to memory without a separate request.
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.
- 18d ago First seen · 19 lines · 40 tokens per session scan A c834975496ff
prevent-repeat-mistakes is a skill published in the GitHub repository EzraApple/skills-init (2 stars, last pushed 19d ago), licensed MIT. It adds 40 tokens to every session and 303 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-16.
Other skills, from other repositories
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
writing-livekit-scenarios
Creates and maintains the scenarios a LiveKit agent simulation runs, and wires the agent to consume them. Use when the user asks "what should I test", "generate simulation scenarios", "write scenarios for my agent", "add a scenario for X", "organize my scenario files", "my simulations are flaky", "the scenario hits my…
running-livekit-simulations
Runs LiveKit agent simulations and acts on the results. Use when the user says "run my simulations", "regression test my agent before deploying", "run the scenarios", "use lk agent simulate", "did my agent pass", "why did this scenario fail", "run simulations in CI", "test the audio pipeline", "check turn-taking and…
dsh-error-handling
A workflow for designing and reviewing how software reports errors, partial success, unknown results, recovery, retries, cancellation, and failure feedback.
dsh-pre-push-checks
A delivery-readiness check for software changes before they are pushed or released. It compares required checks with the actual source, build output, tests, and user-facing behavior.