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-memory-auditgit 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-memory-audit)<a href="https://agentmods.dev/skills/ferroxlabs/ijfw/ijfw-memory-audit"><img src="https://agentmods.dev/badge/skills/ferroxlabs/ijfw/ijfw-memory-audit.svg" alt="Measured on agentmods" 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 | $0.00031 | $0.00427 |
| Opus 5 | $0.00015 | $0.00214 |
| Sonnet 5 | $0.00006 | $0.00085 |
| Haiku 4.5 | $0.00003 | $0.00043 |
Grade A, and why
ijfw-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
Execution
-
Call
ijfw_metricsto get counts and last-update timestamps for all tiers. -
Scan
.ijfw/memory/for all.mdfiles. For each, note:- File name, size (lines), last modified date.
- Days since last referenced (use file mtime as proxy).
-
Categorize entries:
ACTIVE -- referenced within 30 days
STALE -- not referenced in 30-90 days
ARCHIVE -- not referenced in 90+ days, or flagged as superseded
- Report:
MEMORY HEALTH REPORT
Total entries: <N> | Total size: ~<X> lines
Active: <N> | Stale: <N> | Archive candidates: <N>
STALE ENTRIES (>30 days unreferenced)
- <filename>: <one-line summary> [last seen: <date>]
ARCHIVE CANDIDATES (>90 days or superseded)
- <filename>: <one-line summary> [last seen: <date>]
RECOMMENDATION
Archive <N> entries to .ijfw/memory/archive/. No data is deleted.
-
Pruning question: for each entry flagged STALE or ARCHIVE, ask "Would removing this rule cause the agent to make a mistake?" If no, archive. If yes, keep and tighten. Memory that doesn't change behavior is bloat that crowds out memory that does.
-
Ask before acting:
Archive <N> stale entries? (y/n -- files move to .ijfw/memory/archive/, not deleted) -
On confirmation, move flagged files. Store audit result:
ijfw_memory_store: memory audit on <date> -- archived <N> entries
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 · 46 lines · 31 tokens per session scan A 66162f883b5b
ijfw-memory-audit is a skill published in the GitHub repository FerroxLabs/ijfw (210 stars, last pushed today), licensed MIT. It adds 31 tokens to every session and 427 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
Maintain durable, evidence-based repository context whenever an agent initializes a repository, changes behavior, checkpoints or resumes work, switches AI tools or windows, collaborates through Git, prepares a pull request, or completes a coding task. Use the deterministic runtime to route bounded context, isolate…
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.
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…
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…
summary
A skill that writes a summary of the current conversation to a daily memory file before work ends.
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…