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-reflect)<a href="https://agentmods.dev/skills/atman-33/workhub/memory-reflect"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/memory-reflect/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-reflect"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/memory-reflect.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 | $0.00072 | $0.01362 |
| Opus 5.5 | $0.00029 | $0.00545 |
| Sonnet 5.5 | $0.00014 | $0.00272 |
| Haiku 4.5 | $0.00007 | $0.00136 |
Grade A, and why
memory-reflect 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 28d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
memory-reflect — promote what will matter next time
This is the step that makes memory compound. Without it the store only grows: a pile of transcripts and checkpoints that each get less useful as they age. With it, what a session worked out survives as something a later session can find in one query.
Memory is formed best between sessions rather than during one — the work of deciding what mattered is easier once the work is over.
What this may do on its own, and what it may not
The line is reversibility, not importance. memory/identity/decision-policy.md's
gray-zone rule already draws it: reversible → proceed, irreversible → ask.
| Action | Do it |
|---|---|
Write a new note in notes/ or episodes/ |
Without asking. A new file in a git-tracked folder is undone by deleting it |
| Archive a note that is finished | Without asking. A move is reversible, and the note stays in the graph |
| Rewrite or merge an existing note | Propose it. Show what would be lost |
Touch anything in identity/ |
Propose it. It is capped, so adding means removing |
| Delete anything | Don't. Archive instead |
Everything done without asking is reported. End with one line per note written or moved. Something that changes the record silently is indistinguishable from something that is broken — which is exactly how 46 days of capture loss went unnoticed (T-0366).
Steps
1. Gather what is recent
node "${CLAUDE_PLUGIN_ROOT}/engine/cli.mjs" recent --limit 30
Plus the open checkpoints in memory/episodes/ and, when the user names a
subject, memory-recall for that subject.
2. Decide what is worth keeping
Ask of each thing, in order. The first keep wins; anything that reaches the
bottom is dropped.
| Keep | Because |
|---|---|
| A decision with a rationale and an alternative | It stops the same ground being relitigated |
| A lesson — something that went wrong and why | It stops the same failure |
| A constraint discovered the hard way | It is invisible in the code |
| A preference the owner stated as standing, not once | It changes how future work is done |
| The shape of something: how a system is put together, why it is that way | It is the expensive thing to re-derive |
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.
- 28d ago First seen · 132 lines · 72 tokens per session scan A 66d14b28c31d
memory-reflect is a skill published in the GitHub repository atman-33/workhub (3 stars, last pushed 2d ago), licensed MIT. It adds 72 tokens to every session and 1,362 once invoked, about $0.0003 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.