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 GregoryHo/arcforge --skill learninggit clone --depth 1 https://github.com/GregoryHo/arcforgeWrote 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/gregoryho/arcforge/learning)<a href="https://agentmods.dev/skills/gregoryho/arcforge/learning"><img src="https://agentmods.dev/badge/skills/gregoryho/arcforge/learning/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/gregoryho/arcforge/learning"><img src="https://agentmods.dev/badge/skills/gregoryho/arcforge/learning.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 | $0.00022 | $0.01974 |
| Opus 5.5 | $0.00009 | $0.00790 |
| Sonnet 5.5 | $0.00004 | $0.00395 |
| Haiku 4.5 | $0.00002 | $0.00197 |
Grade A, and why
learning 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 today.
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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Learning
The loop runs session → diary → pattern → instinct → activation, and every step
that could change future behavior waits for a person. Learning is off until
someone enables it, and an instinct affects nothing until someone activates it.
Which job
| The user wants | Go to |
|---|---|
| to record what this session decided or discovered | Capturing a diary |
| to know what keeps recurring across sessions | Reflecting over diaries |
| to remember one specific thing, right now | Saving an instinct by hand |
| to see or change what the subsystem has proposed | Reviewing what activates |
For handing unfinished work to the next session, this is the wrong skill —
/sessions writes handovers. A diary is for reflection, not continuity.
Capturing a diary
Step 1 — Check there is something worth recording
At least one must be true: a non-trivial decision was made, a challenge was solved, the user expressed a preference, or a technique was discovered. Pure Q&A, a retried build, exploration that decided nothing, and one-line fixes get no diary. Say so and stop.
- Done when one of the four criteria is named, or the session is declared not worth a diary.
Step 2 — Check for a draft before writing anything
Run arcforge learn diary path --draft --session <id> and read that file if it
exists. A background pipeline writes one after a substantial session.
A draft that exists is the entry — never write a fresh one alongside it. Doing that leaves two diaries for one session: a duplicate final entry and an orphaned draft nobody reads.
Its ## Session Metrics section is already correct — preserve it verbatim.
Then take the enrichable sections one at a time. Which shape you write depends on one thing: were you in that session?
You were — replace the <!-- TO BE ENRICHED --> line with what happened.
You were not — the finished section keeps the marker and gains a note under it:
## Decisions Made
<!-- TO BE ENRICHED -->
_Not recorded — this session is not in this conversation's history._
What ships with it
3 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.
- today First seen · 196 lines · 22 tokens per session scan A e3a1abcbf330
learning is a skill published in the GitHub repository GregoryHo/arcforge (8 stars, last pushed 12d ago), licensed MIT. It adds 22 tokens to every session and 1,974 once invoked, about $0.0001 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 2026-11-07.
learning compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| learningGregoryHo/arcforge | Skill | 8 | 12d ago | MIT | A | 22 | Claude Code, Codex |
| autoreviewopenclaw/clawhub | Skill | 9.5k | yesterday | MIT | A | 17 | Claude Code, Codex |
| agent-teams-simplify-and-hardenLeoYeAI/openclaw-master-skills | Skill | 2.2k | 6d ago | MIT | A | 115 | Claude Code, Codex |
| omh-code-reviewrlaope/oh-my-hermes | Skill | 5.2k | yesterday | MIT | A | 48 | Claude Code, Codex |
| revdiff-planumputun/revdiff | Skill | 945 | yesterday | MIT | A | 84 | Claude Code |
| explore-unknownsdzhng/skills | Skill | 1.4k | 2d ago | MIT | A | 162 | Claude Code, Codex |
| re0-mergeLilMGenius/paperthin | Skill | 1.4k | 4d ago | MIT | A | 70 | Claude Code |