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 Curt-Park/autology --skill autology-workflowgit clone --depth 1 https://github.com/Curt-Park/autologyWrote 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/curt-park/autology/autology-workflow)<a href="https://agentmods.dev/skills/curt-park/autology/autology-workflow"><img src="https://agentmods.dev/badge/skills/curt-park/autology/autology-workflow/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/curt-park/autology/autology-workflow"><img src="https://agentmods.dev/badge/skills/curt-park/autology/autology-workflow.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 | $0.00058 | $0.00430 |
| Opus 5.5 | $0.00023 | $0.00172 |
| Sonnet 5.5 | $0.00012 | $0.00086 |
| Haiku 4.5 | $0.00006 | $0.00043 |
Grade A, and why
autology-workflow 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 2mo 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
Overview
Route to the right autology skill after significant actions. Knowledge captured close to the action is more accurate and complete — this workflow keeps docs/ in sync with what actually happened.
Trigger Points
[Action completed] After commit/push/PR or decision/convention discovered
/autology:triage-knowledge— context triage: analyze action, return classified list + topology hints- In parallel from the same triage result:
- Existing items → batch
/autology:sync-knowledge(use topology hints to verify connected nodes too) - New items → batch
/autology:capture-knowledge(use suggested relations from hints to add wikilinks)
- Existing items → batch
If triage returns only new items (no existing matches), skip sync — capture runs alone. If triage returns only existing items (nothing new), skip capture — sync runs alone.
Signals for "action completed":
- commit, push, PR created
- "decided", "chose", "always", "never", "the rule is", any architectural choice
autology-workflow just completed (skip — do not re-trigger):
- triage-knowledge, sync-knowledge, or capture-knowledge just ran
- docs/*.md file was just written or edited
Flow
Action → triage → sync (existing) + capture (new) → done
Common Mistakes
| Mistake | Fix |
|---|---|
| sync/capture without triage first | Without triage + hints, risk duplicates or missing nodes |
| Ignore topology hints in sync/capture | Use connected/suggested relations to strengthen wikilinks |
| Only capture when user says "remember" | Self-discovered conventions are also capture targets |
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 42 lines · 0 tokens per session scan A 500bc0dec8ac
autology-workflow is a skill published in the GitHub repository Curt-Park/autology (25 stars, last pushed 7mo ago), licensed MIT. It adds 58 tokens to every session and 430 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 2026-08-30.
Other skills, from other repositories
okf-pro
Operating rules for the .okf/ knowledge bundle — filing new concepts, the board, the journal, the daily snapshot, closing work, source attribution, and the generated/verified attestation policy. Use before reading from or writing anything into .okf/.
mama-context
MAMA context at session start; everything else is pulled with the MAMA tools and commands.
mama-install
Install MAMA OS and guide the owner through setup until MAMA answers their first message.
wiki-fold
Roll up the wiki's journal.md entries into structured fold pages — like 2^k log compaction. Reads the last 2, 4, 8, 16... entries and writes a fold page that summarizes them by extractive summarization (no invention), with backlinks to children. Idempotent at the structural level — re-running with the same window…
kb-session-review
Review this session's knowledge base usage. Use when the user asks whether the KB was updated, what was captured, if anything was missed, or wants a session retrospective on knowledge capture quality.
hmem-activate
Switch active project mid-session via loadproject, then fix any misrouted O-entry exchanges. Use when the user says 'aktiviere/lade Projekt X', 'switch to project Y', or whenever you'd otherwise call loadproject mid-session.