ijfw-auto-memorize

ijfw-auto-memorize is a skill for Claude Code from FerroxLabs/ijfw. It costs 37 tokens per session (959 once invoked), scanned C, original, MIT.

A session-end tool that turns detected errors, fixes, lessons, and user feedback into structured local memory. It asks for consent before the first extraction and can use an explicitly configured model.

In plain words
What is it for?
Use it to record recurring mistakes, solutions, preferences, and other lessons from coding sessions for later reference.
Why use it?
It reduces the need to remember useful project knowledge manually while keeping extraction local unless an external model is configured.

Skill for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: positional $N argument; mentions Claude Code.

Part of the ijfw plugin — 34 skills, 22 commands, 37 agents, 6 hooks shipped together

Good fit Use it to record recurring mistakes, solutions, preferences, and other lessons from coding sessions for later reference.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ferroxlabs/ijfw/ijfw-auto-memorize
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.

Any agent
npx skills add FerroxLabs/ijfw --skill ijfw-auto-memorize
Clone the repo
git clone --depth 1 https://github.com/FerroxLabs/ijfw

Made for: Claude Code.

Or install ijfw, the plugin that ships this one along with the rest of its 34 skills, 22 commands, 37 agents, 6 hooks.

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 ijfw-auto-memorize

README.md
[![agentmods](https://agentmods.dev/badge/skills/ferroxlabs/ijfw/ijfw-auto-memorize/github.svg)](https://agentmods.dev/skills/ferroxlabs/ijfw/ijfw-auto-memorize)
Your own site
<a href="https://agentmods.dev/skills/ferroxlabs/ijfw/ijfw-auto-memorize"><img src="https://agentmods.dev/badge/skills/ferroxlabs/ijfw/ijfw-auto-memorize/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.

agentmods 80×15 button for ijfw-auto-memorize

Your own site · 80×15
<a href="https://agentmods.dev/skills/ferroxlabs/ijfw/ijfw-auto-memorize"><img src="https://agentmods.dev/badge/skills/ferroxlabs/ijfw/ijfw-auto-memorize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 959 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00037 $0.00959
Opus 5 $0.00018 $0.00479
Sonnet 5 $0.00007 $0.00192
Haiku 4.5 $0.00004 $0.00096

Measured 5d ago against content hash 603a850eddb3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade C, and why

ijfw-auto-memorize scanned grade C with 1 finding 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

> *Stored 3 new memories: pagination-off-by-one fix, user prefers esbuild, stopped repeating rm -rf warnings.*
claude/skills/ijfw-auto-memorize/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fires at session end. Reads deterministic signals captured during the session and synthesizes structured memories. Nothing leaves the machine unless the user explicitly configured an API model via IJFW_AUTOMEM_MODEL.

Before any synthesis, check .ijfw/.automem-consent:

  • If missing: ask the user once: "IJFW can automatically extract lessons (errors hit, fixes applied, preferences you stated) at session end into local memory. OK? (y/n). Reply y, n, or ask (ask again next time)." Write answer as {"consented": true|false, "at": "<iso>"} to .ijfw/.automem-consent.
  • If "consented": false: do nothing this session.
  • If "consented": true: proceed.

Inputs (all local files)

  • .ijfw/.session-signals.jsonl -- ERROR/FAIL/Traceback lines captured by the PreToolUse hook (W3.6).
  • .ijfw/.session-feedback.jsonl -- corrections/confirmations/preferences detected by the UserPromptSubmit hook (W3.7).
  • .ijfw/.prompt-check-state -- last turn's intent + vague signals.
  • .ijfw/memory/project-journal.md -- existing entries (dedupe against these).
  • Transcript read via Claude Code's Stop-hook payload (transcript_path).

Synthesis

For each signal cluster:

  1. Redact secrets first. Call redactSecrets() from mcp-server/src/redactor.js on every field that came from transcript or tool output.
  2. Cap sizes. Run applyCaps from mcp-server/src/caps.js. content ≤4KB, why/how ≤1KB, summary ≤120.
  3. Dedupe. Use BM25 search (mcp-server/src/search-bm25.js) against project-journal.md. If score > 6 against an existing entry, skip (duplicate).
  4. Classify into one of:
    • pattern -- error→fix recurrence (same error type seen >=2x).
    • decision -- an explicit user choice ("from now on X").
    • preference -- a style/workflow preference ("I prefer Y").
    • observation -- something worth noting, single instance.
  5. Emit via ijfw_memory_store MCP tool with fields:
    • type: one of the above
    • summary: single sentence, ≤120 chars
    • content: the fact + minimal context
    • why: where this came from (e.g., "user said 'don't use X'", or "hit error Y at step Z")
    • how_to_apply: when this should surface in future sessions
    • tags: include auto-memorize and the classifier kind (correction, confirmation, preference, rule, error)

Read the full file on GitHub · 75 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 · 75 lines · 37 tokens per session scan C 603a850eddb3

Subscribe to this mod's changes

ijfw-auto-memorize is a skill published in the GitHub repository FerroxLabs/ijfw (210 stars, last pushed 3d ago), licensed MIT. It adds 37 tokens to every session and 959 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.

Related

Other skills, from other repositories

repo-context-ledger

Record every behavior-changing feature addition, fix, and adjustment as durable, evidence-based repository knowledge, then use that ledger to continue accurately across AI windows, tools, Git collaboration, and pull requests. Use the deterministic runtime to route bounded context, isolate private drafts, publish…

gviiisen/repo-context-ledger · 98 tokens

memory

A session-memory tool with three layers: agent notes, requirement memories, and overall project memory. The description does not specify how these memories are stored or managed.

devcodex-labs/devcodex · 34 tokens

summary

A skill that writes a summary of the current conversation to a daily memory file before work ends.

devcodex-labs/devcodex · 39 tokens

compact-task-memory

Produce a lossy compaction summary of TASKSTATE.md when task memory has grown beyond a useful working size, preserving canonical decisions and recommended next step while dropping stale facts. Distinct from sync-task-state (incremental, append-only, never lossy) and state-reconcile (drift repair, no shrinking). Use…

Mozurok/fhorja.dev · 175 tokens

capture-observation

Append a single observation, question, hypothesis, or concern to TASKSTATE.md as task memory without disrupting in-progress work or requiring a full state sync. Lean append-only; never restructures other artifacts. Use when something surfaces mid-work that should be remembered for later (during planning…

Mozurok/fhorja.dev · 171 tokens

harvest-session-learnings

Scan the current working session and the active task's artifacts for reusable, generalizable lessons (what was tried, what failed and why, what surprised us, what the next task should do differently) and propose anchored entries to append to the task's LEARNINGS.md, the produce-side counterpart to the ADR-0017 consume…

Mozurok/fhorja.dev · 198 tokens