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 Chemaclass/agnostic-ai --skill handoffgit clone --depth 1 https://github.com/Chemaclass/agnostic-aiWrote 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/chemaclass/agnostic-ai/handoff)<a href="https://agentmods.dev/skills/chemaclass/agnostic-ai/handoff"><img src="https://agentmods.dev/badge/skills/chemaclass/agnostic-ai/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/chemaclass/agnostic-ai/handoff"><img src="https://agentmods.dev/badge/skills/chemaclass/agnostic-ai/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 | $0.00014 | $0.02102 |
| Opus 5.5 | $0.00006 | $0.00841 |
| Sonnet 5.5 | $0.00003 | $0.00420 |
| Haiku 4.5 | $0.00001 | $0.00210 |
Grade A, and why
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 2d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
handoff
Write or resume a portable session handoff when the user requests it. Choose the mode from the request: "write a handoff" writes; "resume" or "continue where Codex left off" reads. An explicit argument can select the mode, but is never required. Do not read a handoff at session start without a request. The lead asks each delegate to "write a handoff for " before it returns.
Resolve the current project root, including when this skill is installed globally. For root lookup, use canonical paths for the current directory, candidate ancestors, and the effective global source root (AGNOSTIC_AI_HOME when nonempty, otherwise ~/.agnostic-ai). Find the nearest ancestor containing agnostic-ai.yaml or the legacy agnostic.config.yaml, but exclude the effective global source root: its home config never identifies a project. If none exists, use git rev-parse --show-toplevel for the current checkout. Do not replace a configured subproject root with its Git worktree root. Use portable Markdown.
Task store
Run git worktree list --porcelain to find the main checkout (the first entry), live branches, and their absolute worktree paths. Preserve the project path relative to its Git checkout: a configured subproject uses the same relative path in the main checkout. The shared store is <main checkout>/<project path>/.agnostic-ai/local/handoffs/.
Use one <branch-slug>.md per branch. The branch-slug replaces each character outside [A-Za-z0-9._-] with -; the real branch: header is the key. Read an existing file's header before overwriting it. If a different branch has the same slug, ask which task to keep and wait for the answer. For detached HEAD, use detached-<full HEAD> as the key and add detached: true to the worktree header. A named branch detached keeps its real branch key.
Resolve existing parent directories before checking the destination. Use git check-ignore -q -- <absolute file> in the checkout that owns the store, and refuse tracked files or symlinks. If the main checkout is bare, the shared destination is not ignored, or its write fails, fall back to the current project's .agnostic-ai/local/handoffs/. Apply the same ignore and symlink checks to the fallback. If neither store is safe, report the failure and leave the handoff pending. Never change ignore rules or write a public handoff to get past this check.
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.
- 2d ago Changed · +14 lines c40b79e2ae78
- 9d ago First seen · 59 lines · 14 tokens per session scan A bc0ac2c006c0
handoff is a skill published in the GitHub repository Chemaclass/agnostic-ai (25 stars, last pushed today), licensed MIT. It adds 14 tokens to every session and 2,102 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 2026-10-07.
Other skills, from other repositories
session-end
Close a session — summarize changes, suggest commits, write a journal entry (episodic trace), write fresh NEXT.md (handoff). Chains to dream for substantive sessions.
dream
Sleep-consolidation pass — replay journal entries to distill them into garden/essential/USER.md, garden/essential/SOUL.md, garden/ .md, and new procedures in forge/ (all T1 autonomous within capacity). Propose T2 graduations to 3-control/foundation/SOUL.md, 3-control/foundation/PRINCIPLE.md, and 3-control/rule/ for…
session-start
Load read order into agent context at every session begin. Invoke detect-runtime in drift-check mode and propose re-ratify on runtime mismatch with profile.md. Consume + clear NEXT.md (the working buffer). Brief Owner on state. Not the one-time bootstrap (use init for that).
tldr-compress
Compress natural language memory files (CLAUDE.md, todos, preferences) into TLDR format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /tldr-compress FILEPATH or "compress…
agent-v3-memory-specialist
Agent skill for v3-memory-specialist - invoke with $agent-v3-memory-specialist.
memory-retain
Save what was learned to Hindsight long-term memory. Use when a task finishes, when the user states a fact, decision or preference, and when you discover something a later run or another Bot would need.