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 sessionsgit 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/sessions)<a href="https://agentmods.dev/skills/gregoryho/arcforge/sessions"><img src="https://agentmods.dev/badge/skills/gregoryho/arcforge/sessions/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/sessions"><img src="https://agentmods.dev/badge/skills/gregoryho/arcforge/sessions.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 | $0.02008 |
| Opus 5.5 | $0.00025 | $0.00803 |
| Sonnet 5.5 | $0.00013 | $0.00402 |
| Haiku 4.5 | $0.00006 | $0.00201 |
Grade A, and why
sessions 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sessions
Context stops being available two ways: the session ends, or it gets compacted. Both lose the same thing — everything that was only ever in the conversation — and both are answered the same way, by getting that content onto disk first.
A handover is written for a reader who was not here — the next session, tomorrow's you, a teammate. What they can reconstruct from the repo stays out of it. What they cannot — why it stopped, what was decided and against what, which parts have been proven and which only look finished — is the whole content.
Every step below carries a completion criterion. Do not start the next one until the current one is checked off.
Writing a handover
Step 1 — Establish what is actually verified
Run the project's test or build command in this working tree and read the result. Then put every piece of work in flight into one of three states: verified by a run you just watched, written but never exercised, or not started.
A green suite is evidence about the code the suite covers and nothing else. Work that no test touches is unverified however green the run was, and an untested file that reads as complete is the single thing a handover most often gets wrong. Second-hand status counts the same way: work someone described as finished is verified when a run says so and not before.
- Done when the suite has been run here and every piece of work in flight carries one of the three labels.
Step 2 — Write the file
Open references/handover-template.md and write .handovers/<YYYY-MM-DD>-<slug>.md
from it: five sections in this order — Where it stands, Done, Unfinished,
Decisions, Next — every slot filled, the word none in a slot with nothing in
it, never a deleted heading. The file is an ordinary project file: commit it when
the handoff is to someone else, ignore it when it is to yourself tomorrow.
- Done when the file exists at that path, no slot holds a placeholder, and the user has been told the path and the next action.
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 · 155 lines · 63 tokens per session scan A 951cd2d8ab6f
sessions is a skill published in the GitHub repository GregoryHo/arcforge (8 stars, last pushed 12d ago), licensed MIT. It adds 63 tokens to every session and 2,008 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 2026-11-07.
sessions compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| sessionsGregoryHo/arcforge | Skill | 8 | 12d ago | MIT | A | 63 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |