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 chrono-meta/forge-harness --skill memory-hygienegit clone --depth 1 https://github.com/chrono-meta/forge-harnessWrote 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/chrono-meta/forge-harness/memory-hygiene)<a href="https://agentmods.dev/skills/chrono-meta/forge-harness/memory-hygiene"><img src="https://agentmods.dev/badge/skills/chrono-meta/forge-harness/memory-hygiene.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 6 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- medium Rogue Agent · line 146 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00065 | $0.02756 |
| Opus 5 | $0.00032 | $0.01378 |
| Sonnet 5 | $0.00013 | $0.00551 |
| Haiku 4.5 | $0.00006 | $0.00276 |
Grade A, and why
memory-hygiene 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
memory-hygiene — Stale Memory Detection and Re-Verification
Addresses the "stale-but-confident" failure mode: verified information that silently drifts while remaining highly ranked in retrieval — identified as a harness failure mode in Scaling the Harness in Agentic AI (arXiv:2605.26112).
Sister asset: arXiv:2607.01935 (A-TMA: Decoupling State-Aware Memory Failures in Long-Term Agent Memory, Shi/Tang/Tung 2026) names this exact class "ghost memory" — outdated / current / transitional facts intermixing during retrieval — and benchmarks it (LTP; conflict-accuracy +0.240, temporal-F1 0.03→0.17 on LoCoMo with a bank-maintenance layer). It is the tighter external frame for what memory-hygiene detects: this skill is the FH-native detection + archival pass over the same failure A-TMA formalizes at the retrieval layer. (Source-verified 2026-07-03; a broader bounded-memory testbed, arXiv:2607.02255 AgenticSTS, was considered and set aside — it targets context-assembly, not staleness, so it is not the sister here.)
FH is an online-first harness. Its memory entries point to live external resources (GitHub repos, arXiv records, Zenodo DOIs, monitoring routines). These drift faster than in offline systems — which makes hygiene both more necessary and more tractable (live re-verification is possible).
Trigger Conditions
Natural Language Triggers
| Phrase | Intent |
|---|---|
| "memory check", "check stale memories" | Manual hygiene scan |
| "are my memories still accurate?" | Full re-verification pass |
| "clean up memory", "memory audit" | Propose archival candidates |
| "something in memory might be wrong" | Targeted re-check |
Automatic Trigger
- harvest-loop Step 0-c: Runs automatically as the first step of every full harvest-loop
- Cadence guard: Skip if memory-hygiene ran within the last 7 days
(
tracks/_meta/memory_hygiene_*.mdmtime check)
Staleness Classification
| Type | Staleness Threshold | Re-verification Method |
|---|---|---|
project — status/milestone entries |
14 days | Re-read source file or live resource |
reference — external URLs, DOIs, GitHub repos |
30 days | WebFetch or gh CLI check |
feedback — operating rules |
90 days | Grep for contradicting evidence in recent sessions |
user — user profile entries |
180 days | Flag only, no auto-verification |
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.
- 8d ago First seen · 211 lines · 65 tokens per session scan A 79d8b162379d
memory-hygiene is a skill published in the GitHub repository chrono-meta/forge-harness (14 stars, last pushed today), licensed MIT. It adds 65 tokens to every session and 2,756 once invoked, about $0.0003 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 skills, from other repositories
taiyi-compress
A workflow tool for shrinking large coding-agent conversations and work files into shorter context notes. It can also coordinate separate agents for parallel development and create handoff notes for continuing work in a new session.
okf
Author, maintain, and consume Open Knowledge Format (OKF) knowledge bundles — portable markdown + YAML frontmatter that both humans and agents read. Use when capturing project knowledge (services, APIs, schemas, metrics, runbooks, decisions) into an OKF bundle, when updating one after code or docs change, or when a…
remem
Use when the user asks Codex to recall prior project context, save durable decisions or bug fixes, inspect remem memory health, or activate remem automatic memory hooks from the Codex plugin.
orient
Use when user invokes /orient with a topic keyword, entity type, project name, time qualifier, or combination. Also triggers on "what do we know about X", "remind me about X", "where did we leave off on X". Provides targeted context loading — searches the MCP Memory Server graph, knowledge files, journal entries, and…
memory
Use when user invokes /memory with a subcommand (search, trace, add, episode, status). Also triggers on "search my memory for X", "add to memory", "what do I know about X" (when membrain is available), "memory status", "memory trace". Searches and manages the membrain knowledge graph via MCP tools or HTTP API.
capture
Use when user invokes /capture to capture information from the current conversation into a staging file for later reflection and knowledge graph processing. Accepts no arguments (auto-extract), specific facts as text, or filter keywords like "decisions" or "technical". Do NOT use when the user wants to write directly…