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 azusachino/harus-skills --skill revisegit clone --depth 1 https://github.com/azusachino/harus-skillsWrote 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/azusachino/harus-skills/revise)<a href="https://agentmods.dev/skills/azusachino/harus-skills/revise"><img src="https://agentmods.dev/badge/skills/azusachino/harus-skills/revise/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/azusachino/harus-skills/revise"><img src="https://agentmods.dev/badge/skills/azusachino/harus-skills/revise.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 | $0.00018 | $0.01129 |
| Opus 5 | $0.00009 | $0.00564 |
| Sonnet 5 | $0.00004 | $0.00226 |
| Haiku 4.5 | $0.00002 | $0.00113 |
Grade A, and why
revise 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 3d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Revise
Persist durable lessons from the current work into the asobi graph. The Asobi skill's session closeout records where we are; this records what should change future behaviour.
When to use
After a meaningful discovery — a workflow worth repeating, a non-obvious project fact, or (most importantly) a dead end an agent should not re-walk. Capture while context is fresh. Not for ordinary task status, which belongs in session closeout.
Classify
Read the user's free-form text and classify it yourself; ask only if it is too vague to preserve. Keep each lesson short and actionable — "do X because Y", not a transcript.
| Class | Means | Destination |
|---|---|---|
work-experience |
how work was actually done | [project] observation |
finding |
a non-obvious fact or gotcha (an architectural choice → a decision entity, per the Asobi skill) | [project] observation |
wrong-approach |
something tried and rejected | [project]:pitfall:<slug> entity |
Flow
- Detect asobi:
command -v asobi. If absent, use the fallback files below. - Derive
[project]from the owning repository and confirm graph scope using the Asobi skill's discovery rules. Ancestor configuration can select a parent workspace graph. Use the intended graph; do not initialize or migrate state as a side effect of lesson capture. - Dedup first:
asobi search "<topic>" --limit 10. Inspect matching entities. Appendseen-again YYYY-MM-DD: <evidence>only for genuinely new evidence; skip an unchanged repeat. If the lesson contradicts an old one, record the correction and resolve the obsolete pitfall rather than reinforcing it. - Write — ensure the project entity exists (
asobi new "[project]" "project"), then:
For a wrong-approach, write the pitfall entity below.asobi obs "[project]" "experience YYYY-MM-DD: <lesson>" # work-experience asobi obs "[project]" "finding YYYY-MM-DD: <lesson>" # finding - Confirm in one line.
Pitfall entity
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.
- 3d ago Changed · -2 lines a46c2466dab1
- 4d ago Changed 721d662bc870
- 12d ago First seen · 76 lines · 18 tokens per session scan A 8a71eeaa12db
revise is a skill published in the GitHub repository azusachino/harus-skills (5 stars, last pushed yesterday), licensed MIT. It adds 18 tokens to every session and 1,129 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.