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 agentmods add commands/ferroxlabs/ijfw/memory-auditgit clone --depth 1 https://github.com/FerroxLabs/ijfwWhat 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 | $0.00021 | $0.00212 |
| Opus 5 | $0.00010 | $0.00106 |
| Sonnet 5 | $0.00004 | $0.00042 |
| Haiku 4.5 | $0.00002 | $0.00021 |
Grade A, and why
memory-audit 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 2d 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
List recent entries tagged auto-memorize from .ijfw/memory/knowledge.md and ~/.ijfw/memory/global/*.md. Show newest first, grouped by kind (correction/confirmation/preference/rule/error).
Format per entry:
[YYYY-MM-DD] <kind> -- <summary>
why: <why line>
how: <how-to-apply>
tags: <tags>
If the user asks to remove an entry, surface the exact file and line so they can delete or edit manually. Do not silently modify memory files -- let the user do that so they see what's changing.
When no auto-entries exist: "No auto-memorized entries yet. Enable with IJFW_AUTO_MEMORIZE=on or run a session with signals."
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.
- 2d ago First seen · 19 lines · 21 tokens per session scan A a0f44c13b77f
memory-audit is a command published in the GitHub repository FerroxLabs/ijfw (210 stars, last pushed 9d ago), licensed MIT. It adds 21 tokens to every session and 212 once invoked, about $0.0001 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 commands, from other repositories
constitution
根据交互输入或已提供原则创建或更新项目章程，并确保相关模板保持同步。.
meta-theory-verify
Run the appropriate MetaKim verification path.
core-review
Review code changes against SpecOps project-specific patterns. Catches recurring failure modes from real PRs — tool abstraction violations, generated file drift, cross-platform gaps, variable inconsistencies, and more. Complements full-review-gate (generic quality) and pr-fix (applying bot comments).
resolve-conflicts
Resolve merge conflicts on a GitHub PR by merging the base branch into the PR branch in an isolated git worktree, with JSON/markdown-aware conflict resolution.
ship-pr
Commit all changes to a new branch, push, and open a PR for review. The original branch stays clean.
ship
Commit all changes and push to remote in one operation (combines /commit and /push).