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 NickCirv/engram --skill mistakesgit clone --depth 1 https://github.com/NickCirv/engramWrote 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/nickcirv/engram/mistakes)<a href="https://agentmods.dev/skills/nickcirv/engram/mistakes"><img src="https://agentmods.dev/badge/skills/nickcirv/engram/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/nickcirv/engram/mistakes"><img src="https://agentmods.dev/badge/skills/nickcirv/engram/mistakes.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00046 | $0.00726 |
| Opus 5.5 | $0.00018 | $0.00290 |
| Sonnet 5.5 | $0.00009 | $0.00145 |
| Haiku 4.5 | $0.00005 | $0.00073 |
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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- mistakes — 100% identical, 0 lines differ
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.
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.
- 1mo ago First seen · 55 lines · 46 tokens per session scan A 45797dab6bf9
mistakes is a skill published in the GitHub repository NickCirv/engram (143 stars, last pushed 3d ago), licensed Apache-2.0. It adds 46 tokens to every session and 726 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 2026-08-30.
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.
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.
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…
nexus-memory
Persistent memory for Claude Code backed by Qdrant. Auto-Recall injects relevant memories before each prompt. Auto-Capture stores facts after each turn, automatically. Storage is a local Qdrant instance; embeddings run fully local by default through the local Nexus service (sentence-transformers with…
kiro-steering-custom
Create custom steering documents for specialized project contexts.
memory-import
Bulk-import an external knowledge base into Prismer memory via the three-layer import pipeline (07 §3.1). Use when the user asks to import/migrate documents, a knowledge base, or notes into workspace memory. Layer 1 lands raw documents (zero LLM, instantly searchable); Layer 2 is YOUR distillation work — you read the…