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 takaoumehara/superforge-skill --skill superforge-handoffgit clone --depth 1 https://github.com/takaoumehara/superforge-skillWrote 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/takaoumehara/superforge-skill/superforge-handoff)<a href="https://agentmods.dev/skills/takaoumehara/superforge-skill/superforge-handoff"><img src="https://agentmods.dev/badge/skills/takaoumehara/superforge-skill/superforge-handoff/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/takaoumehara/superforge-skill/superforge-handoff"><img src="https://agentmods.dev/badge/skills/takaoumehara/superforge-skill/superforge-handoff.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 | $0.00229 | $0.01584 |
| Opus 5 | $0.00114 | $0.00792 |
| Sonnet 5 | $0.00046 | $0.00317 |
| Haiku 4.5 | $0.00023 | $0.00158 |
Grade A, and why
superforge-handoff 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 9d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Superforge Handoff — Cross-Model Session Transition Protocol
Use this skill whenever switching AI models, before clearing long chat threads, or when ending a work session. It writes a structured handoff capsule to .handoff/ so any AI model can instantly resume work.
1. Triggering Handoff (/handoff or /superforge-handoff)
- Ensure directory
.handoff/exists. - Create capsule file:
.handoff/YYYY-MM-DD-<slug>.md. - Populate the Resume Capsule (under 80 lines):
- Project & Passphrase (
<repo>: <catchy phrase>) - Objective & Verified State
- Running Processes & Active Ports
- The
docs/ledger — see below. This is the part that carries the decisions; without it the capsule carries the conversation instead - Immediate Next Steps
- Files to Read First
- Project & Passphrase (
The docs/ ledger — do not skip this
List every file in docs/, not a summary of them. One row each, read from
the file's own header block:
## docs/
| File | Status | Last updated | Open questions |
|---|---|---|---|
| superforge.md | agreed | 2026-07-29 | — (会話=日本語 / ファイル=英語) |
| product-idea.md | agreed | 2026-07-30 | none |
| business-model.md | draft | 2026-07-31 | pricing tier 3 undecided |
| design.md + design.html | agreed | 2026-07-31 | — |
| accessibility.md | draft | 2026-07-29 | 3 criteria not assessed |
| verification.md | — | — | **not run yet** |
| security.md | FINDINGS-OPEN | 2026-07-31 | 1 High 未対応 |
| ship-readiness.md | — | — | **not run yet** |
| failforward.md | 6 entries | 2026-07-31 | 1 mitigation, cause still unknown |
Five rules that make this worth writing:
superforge.mdgoes first, and its language settings travel with it. A resumed session that starts replying in the wrong language has lost something the user set explicitly, and will be corrected manually every time.- A file that does not exist gets a row saying so. "verification.md — not run yet" is the single most useful line in the capsule, because it tells the next session what has not been proven. A missing row reads as "handled."
- Copy the
StatusandLast updatedfrom each file's own header, not from memory. A capsule that claimsagreedfor something still markeddraftis worse than no capsule. - Carry every
## Open questionssection forward. Those are exactly the decisions an unattended run is allowed to make with a logged default — losing them means the next session either re-asks or re-decides silently. failforward.mdis the one row that is a count, not a status. Note the number of entries and, specifically, any mitigation shipped without a root cause — an open failure the next session would otherwise rediscover the hard way.
What ships with it
7 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.
- 9d ago First seen · 142 lines · 229 tokens per session scan A db0c44ab8c50
superforge-handoff is a skill published in the GitHub repository takaoumehara/superforge-skill (1 stars, last pushed 24d ago), licensed MIT. It adds 229 tokens to every session and 1,584 once invoked, about $0.0011 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
neo4j-agent-memory-skill
Authoritative reference for the neo4j-agent-memory Python package — a graph-native memory system for AI agents built on Neo4j — and for the hosted service (NAMS) at memory.neo4jlabs.com. Use this skill whenever the user mentions neo4j-agent-memory, agent memory with Neo4j, context graphs, the POLE+O model…
lov-auto-context
Manual or hook-triggered context operator. Evaluates the current session for pollution (long conversations, topic drift, stale noise), AND takes concrete context-shaping actions: writing project memory, updating global or project CLAUDE.md (with diff + confirm), and recommending harness commands like /fork, /compact…
lov-search-chat
A local search tool for recalling relevant parts of earlier AI conversations from an indexed memory store. It returns matching sessions and identifiable excerpts from the original conversations.
context-degradation
Recognize patterns of context failure: lost-in-middle, poisoning, distraction, and clash.
context-compression
Design and evaluate compression strategies for long-running sessions.
context-optimization
Apply compaction, masking, and caching strategies.