Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add atman-33/workhub/plugin install memoryWrote 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/atman-33/workhub/memory-tidy)<a href="https://agentmods.dev/skills/atman-33/workhub/memory-tidy"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/memory-tidy/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/atman-33/workhub/memory-tidy"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/memory-tidy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00060 | $0.01352 |
| Opus 5.5 | $0.00024 | $0.00541 |
| Sonnet 5.5 | $0.00012 | $0.00270 |
| Haiku 4.5 | $0.00006 | $0.00135 |
Grade A, and why
memory-tidy 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 17d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
memory-tidy — forgetting, on purpose
Promotion without forgetting just makes a bigger pile. identity/ is read in
full on every session, so its size is not a matter of taste: a note nobody can
read in one pass stops being read at all, and then the judgement it holds stops
applying.
So the layers have caps, and reaching one is the signal to consolidate. The cap
is the mechanism — not a tidiness rule, and not a number to raise when it gets
inconvenient. It already works: memory/identity/decision-policy.md has held to "50
entries, 3 lines each, a fifty-first arrives by merging or dropping one" and it
is the one part of the harness that has never bloated. What the number cannot
tell you is which entries still earn their place — for that, step 1 also asks
which ones nobody has cited.
What this may do on its own
| Action | Do it |
|---|---|
| Archive a finished or superseded note | Without asking. Reversible, and it stays in the graph |
| Add a missing link between two notes | Without asking |
| Merge two notes, or rewrite one | Propose it. Show what would be lost |
Change anything in identity/ |
Propose it. Always |
| Delete | Don't. Archive instead — a deleted note takes its observations and its inbound links with it, and they break silently on the other side |
Report everything done without asking, one line each.
Steps
1. Measure
node "${CLAUDE_PLUGIN_ROOT}/engine/cli.mjs" doctor
| Cap | Limit | Why that one |
|---|---|---|
identity/ notes |
8 | Read in full, every session |
One identity/ note |
120 lines | The same. decision-policy.md is exempt |
decision-policy.md entries |
50, 3 lines each | Counted across every section, not per section |
episodes/ notes |
60 | Past this, promotion has stopped happening |
A cap is a prompt to consolidate, never a licence to delete.
Then ask which policy entries are dead weight:
node "${CLAUDE_PLUGIN_ROOT}/engine/cli.mjs" axes
It lists the entries — ## Always ask excepted — that no note in
memory/notes/ or _ai/comms/ has cited by P-NN in the last 90 days. It says
nothing until 90 days have passed since the policy's axes_since, because an
empty record would otherwise read as "nothing is used". These are candidates for
moving down to notes/, not a verdict: an entry can be rarely reached and still
right. Propose each one with what it would cost to lose, and one of three
outcomes:
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.
- 17d ago Changed · +24 lines 074ec23a8d3b
- 28d ago First seen · 94 lines · 60 tokens per session scan A 49ad157c67af
memory-tidy is a skill published in the GitHub repository atman-33/workhub (3 stars, last pushed 2d ago), licensed MIT. It adds 60 tokens to every session and 1,352 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-19.
Other skills, from other repositories
garden-tending
Tend the knowledge garden — diagnose vault health, condense project memos into project.md overviews, create/merge cross-project topics, fix broken links, archive superseded notes, extend trails. Trigger on "tend the garden", "condense", "update project overview", "check vault health", "where are we with X?", "what…
curator-practice
Operating philosophy for autonomous memex curator tending — orientation protocol, signal triage, bounded work units, initiative thresholds, logging conventions. Trigger on cron-launched runs with no user prompt, "use your judgment", "tend without instructions", "do a pass on the vault", "I'll be away — do what needs…
memo-writing
How to write effective session memos — format, frontmatter schema, observation extraction, topic-signal append. Trigger on /memex:save, "save this for later", "remember this", "save what we discussed", "document this session", "create a memo", or when the [memex] activity nudge appears in context. Do NOT trigger for…
recall
Retrieve session memory across 4 modes — TEMPORAL (date browsing), KEYWORD (FTS lookup), DEEP (cross-session synthesis), LOAD (specific file). Trigger on "what did I do yesterday/last week", "why did we...", "remind me...", "find the memo about...", "last time we...", "patterns across projects", "load the X topic". Do…
trellis-update-spec
Captures executable contracts and coding conventions into .trellis/spec/ documents. Use when learning something valuable from debugging, implementing, or discussion that should be preserved for future sessions.
trellis-session-insight
A tool for searching earlier AI conversations through the Trellis memory command-line tool. It retrieves previous discussions, decisions, and solutions related to the current work.