mistakes

mistakes is a skill for Claude Code, Codex from NickCirv/engram. It costs 46 tokens per session (726 once invoked), scanned A, original, Apache-2.0.

A project-memory skill that lists known past failures, regressions, and incorrect assumptions. It can also show when an old mistake stopped being relevant.

In plain words
What is it for?
Use it before refactoring, while investigating an error, or when learning an unfamiliar part of the codebase.
Why use it?
It helps prevent repeating problems that the project has already encountered, especially before a large change or during debugging.

Skill for Claude CodeCodex

Part of the engram plugin — 3 skills, 1 MCP server shipped together

Install

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.

agentmods
npx agentmods add skills/nickcirv/engram/mistakes
Any agent
npx skills add NickCirv/engram --skill mistakes
Clone the repo
git clone --depth 1 https://github.com/NickCirv/engram

Made for: Claude Code, Codex.

Or install engram, the plugin that ships this one along with the rest of its 3 skills, 1 MCP server.

Wrote 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.

agentmods badge for mistakes

README.md
[![agentmods](https://agentmods.dev/badge/skills/nickcirv/engram/mistakes.svg)](https://agentmods.dev/skills/nickcirv/engram/mistakes)
Your own site
<a href="https://agentmods.dev/skills/nickcirv/engram/mistakes"><img src="https://agentmods.dev/badge/skills/nickcirv/engram/mistakes.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 726 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00046 $0.00726
Opus 5 $0.00023 $0.00363
Sonnet 5 $0.00009 $0.00145
Haiku 4.5 $0.00005 $0.00073

Measured 5d ago against content hash 45797dab6bf9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 5d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • mistakes — 100% identical, 0 lines differ
plugins/anthropic-marketplace/engram/skills/mistakes/SKILL.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

engram mistakes

Surface bi-temporal mistake memory from engram's graph. Each mistake has a valid_until timestamp and an invalidated_by_commit reference, so an old mistake auto-expires when its underlying cause is fixed.

Run:

engram mistakes -p $CLAUDE_PROJECT_DIR

The output lists active (still-valid) mistakes with confidence scores. When a mistake matches a query, engram surfaces it with ⚠️ at the top of the context packet, weighted 2.5× to ensure it gets attention.

Use this skill:

  • Before refactoring a module: "are there known sharp edges here?"
  • During debugging: "has this kind of error been seen before?"
  • When onboarding to a new area of the codebase: "what's broken or fragile?"

To record a new mistake explicitly:

engram learn "Don't pass options.scope=user; SETTINGS_LOCAL takes precedence." -p $CLAUDE_PROJECT_DIR

Example invocations

User: "I'm about to refactor the rate limiter — anything I should know?" You: Run engram mistakes -p $CLAUDE_PROJECT_DIR. Filter mentally for entries related to "rate", "limit", "mutex", or the file paths the user mentions. Surface the matches with their confidence scores: "engram has 3 active mistakes near this code, and one of them flagged this exact module:"

User: "Why does this test keep flaking?" You: Run engram mistakes -p $CLAUDE_PROJECT_DIR. Look for entries about flakiness, timing, race conditions, or the test file's name. If a related mistake exists, quote it verbatim — chances are someone already debugged this.

User: "We just fixed a race condition in the queue worker. Remember it for next time." You: Run engram learn "Queue worker had a race condition: don't read state.queue inside the await; snapshot it first" -p $CLAUDE_PROJECT_DIR. Confirm to the user that the mistake is recorded and will surface with ⚠️ on future Edits to that file.

User: "Has anyone fixed this kind of bug before?" You: Run engram mistakes -p $CLAUDE_PROJECT_DIR. The graph carries 2.5x relevance boost on matching results, so if a similar fix exists, it surfaces near the top.

Read the full file on GitHub · 55 lines

Changes

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.

  1. 5d ago First seen · 55 lines · 46 tokens per session scan A 45797dab6bf9

Subscribe to this mod's changes

mistakes is a skill published in the GitHub repository NickCirv/engram (141 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 46 tokens to every session and 726 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

chatcrystal-task-writeback

Write reusable ChatCrystal task memories after substantive work completes. Use when implementation or debugging produced a durable fix, pitfall, pattern, or decision worth preserving, and when the environment can either persist it through writetaskmemory or emit a structured memory candidate for later save.

ZengLiangYi/ChatCrystal · 62 tokens

chatcrystal-debug-recall

Recall ChatCrystal memories for debugging tasks involving failing tests, compiler errors, runtime exceptions, dependency issues, environment breakage, or performance regressions. Use when historical root causes, fixes, or pitfalls may accelerate diagnosis before proposing a fix.

ZengLiangYi/ChatCrystal · 54 tokens

chatcrystal-task-recall

Recall project-first and global-supplement ChatCrystal memories before substantive implementation, refactoring, migration, configuration, investigation, or optimization work. Use when the task is non-trivial, has repository or project context, and prior fixes, decisions, pitfalls, or reusable patterns may change the…

ZengLiangYi/ChatCrystal · 66 tokens

nexus-memory

Persistent memory for Claude Code powered by Qdrant. Auto-Recall injects relevant memories before each prompt. Auto-Capture stores facts after each turn. Self-hosted, private, works alongside Hermes and OpenClaw with the same Qdrant collection. Configure via NEXUS environment variables. Use when the user asks to…

Neboy72/nexus-memory · 92 tokens

ux-ui-analyze-single-page

Analyze exactly one captured UI page (from uxuimap screenshots + request JSON) and immediately write/update uxuimap/pages/{page}.md in neutral descriptive language. Use when asked to analyze screenshots, rewrite corresponding analysis immediately, or avoid memory/context saturation.

raphaelmansuy/edgequake · 58 tokens

karpathy-llm-wiki

Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.

Astro-Han/karpathy-llm-wiki · 67 tokens