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 atman-33/workhub --skill capture-rulegit clone --depth 1 https://github.com/atman-33/workhubWrote 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/capture-rule)<a href="https://agentmods.dev/skills/atman-33/workhub/capture-rule"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/capture-rule/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/capture-rule"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/capture-rule.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 | $0.00063 | $0.01252 |
| Opus 5.5 | $0.00025 | $0.00501 |
| Sonnet 5.5 | $0.00013 | $0.00250 |
| Haiku 4.5 | $0.00006 | $0.00125 |
Grade A, and why
capture-rule 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 1mo 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Capture Rule
Route durable knowledge to the home where it will auto-inject when next relevant.
Step 1 — Qualify the insight
Capture only knowledge that is reusable and non-obvious from code, git history, or existing instruction files: gotchas, build/tooling quirks, design invariants, conventions, the "why" behind a decision.
Skip (and tell the user why) if it is: a one-off fact for this task only, already documented in the repo, or plainly derivable by reading the code. If it does not qualify, stop here.
Establish the target repository the insight is about. If unclear, infer from the files touched this session and confirm with the user.
Step 2 — Route to a home
Pick exactly one:
The question is when the insight has to reach a session, not what it is about. There are three answers, and they are exhaustive:
| It has to arrive… | Home |
|---|---|
| when a matching file is touched — a constraint about particular code | that repo's .claude/rules/<slug>.md |
| the same, but the rule cannot live in that repo | harness .claude/rules-ex/<slug>.md |
| when the question makes it relevant — everything else durable | the vault's memory/notes/, as a typed note |
A rule fires on a path and costs nothing until that path is opened; a memory
note is found by searching and costs nothing until someone looks. Anything
that does not need to arrive while a specific file is open belongs in memory,
where it is typed, searchable, in git and checked by memory-doctor.
If the home is memory/notes/, do not write a rule file. Write the note
(cli.mjs new lesson "…" from the memory plugin), or tell the user that is
where it belongs and stop.
Auto-memory is deliberately not on this list. It is per-project, local,
invisible and outside git — memory/notes/ does the same job better on every
axis, and keeping both would mean choosing between them every time, which is a
routing decision with no rule behind it.
Knowledge about the harness's own machinery is a memory note too, unless it has
to fire on a path — the vault's .claude/rules/vault-harness-local.md is the
home for the ones that do. Never write to vault-harness.md beside it: that
file is app-managed, so an edit turns into a conflict on the next template
update and ends up in a .bak nobody reads.
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.
- 1mo ago Changed · +19 lines 24bc3253a069
- 1mo ago First seen · 101 lines · 63 tokens per session scan A c4748d99ac2a
capture-rule is a skill published in the GitHub repository atman-33/workhub (3 stars, last pushed 3d ago), licensed MIT. It adds 63 tokens to every session and 1,252 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 2026-08-31.
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…
superbrain-distill
Internal SuperBrain skill — run by the detached capture child to distill a session-event delta into routed Obsidian notes. Not for direct user invocation.
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.