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 FerroxLabs/ijfw --skill ijfw-recallgit clone --depth 1 https://github.com/FerroxLabs/ijfwWrote 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/ferroxlabs/ijfw/ijfw-recall)<a href="https://agentmods.dev/skills/ferroxlabs/ijfw/ijfw-recall"><img src="https://agentmods.dev/badge/skills/ferroxlabs/ijfw/ijfw-recall/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/ferroxlabs/ijfw/ijfw-recall"><img src="https://agentmods.dev/badge/skills/ferroxlabs/ijfw/ijfw-recall.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 | $0.00040 | $0.00321 |
| Opus 5 | $0.00020 | $0.00161 |
| Sonnet 5 | $0.00008 | $0.00064 |
| Haiku 4.5 | $0.00004 | $0.00032 |
Grade A, and why
ijfw-recall 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 4d 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
Execution
-
Call
ijfw_memory_recallwith the current task or goal as the query. If no specific query, use the last user message or the project name. -
Also call
ijfw_metricsto get tier sizes and last-update timestamps. -
Present findings grouped by tier:
WORKING MEMORY (hot -- .ijfw/memory/)
<N> entries found
- <key>: <one-line summary> [<date>]
...
PROJECT MEMORY (project-level decisions)
- <key>: <one-line summary> [<date>]
...
NOTHING RECALLED
Clean slate -- no relevant entries found for "<query>".
Start a session to begin building memory.
- After presenting, offer in one line:
<N> things recalled. Want the full text of any entry? (name it)
Rules
- Never dump raw file contents. Summarize each entry to one line.
- If memory is empty or the MCP tool is unavailable, check
.ijfw/memory/knowledge.mddirectly -- it is plain markdown. - Omit tiers with zero matches. Show "Clean slate" only when all tiers are empty.
- Do not fabricate entries. If recall returns nothing, say so clearly.
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.
- 4d ago First seen · 40 lines · 40 tokens per session scan A 967e76576506
ijfw-recall is a skill published in the GitHub repository FerroxLabs/ijfw (210 stars, last pushed 2d ago), licensed MIT. It adds 40 tokens to every session and 321 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 2026-09-05.
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…
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.
summary
A skill that writes a summary of the current conversation to a daily memory file before work ends.
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…
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…
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…