agentsclimarketplace

Handoff

Skill menot-you/n-soul/skills/handoff

Memory-safe engineering-peer plugin for Claude Code + Codex: 11 skills, 6 bounded agents, 4 hooks. Claims only what it can prove; closes every turn with one next action.

Install
npx -y skills add menot-you/n-soul --skill handoff

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 15 days oldThe repository was created 15 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Persist exact continuation state so a cold engineer can resume safely without relying on chat history or reconstructing hidden decisions.

SKILL.md

1.9 KB, 391 tokens by cl100k_base, as published. Nobody here has run it

Handoff

Use when work crosses sessions, owners, machines, or a human gate. A handoff is durable execution state, not a narrative diary. It must let a cold continuation see one active result, the first real blocker, and the exact next safe action without rereading chat.

Gather live truth

Read the current state before writing:

  • repository and worktree path;
  • branch, base, head commit, and dirty files;
  • pull request, issue, check, and release state when present;
  • active owner and exclusive touched surfaces;
  • locked result, scope, constraints, and authority;
  • completed work with observed verification;
  • open work and first real blocker;
  • failed approaches and why they were rejected;
  • exact next safe action and stop conditions.

Do not trust an older handoff when live state is cheap to verify.

Write the durable record

Use this order:

  1. Result — observable state sought.
  2. Current state — exact branch, commit, worktree, candidate, and external artifacts.
  3. Ownership — allowed and forbidden surfaces.
  4. Decisions — locked choices and rationale.
  5. Completed — proof-backed facts only.
  6. Open — required gaps, ordered by dependency.
  7. Blocker — mechanism, owner, and what clears it.
  8. Next action — one command, file, or decision.
  9. Verification — commands and expected observations.
  10. Rollback and hazards — recovery path and actions not to repeat.

Use absolute paths and immutable identifiers where practical. Never copy secrets. Separate observed, inferred, and unverified claims.

Readback

Re-read the record as a cold continuation. It passes only if the next engineer can resume without asking where the work lives, what is safe to touch, what was proven, what remains blocked, or what happens next.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most agent orchestration skills give in 391 tokens

Counted across 742 of the 995 authors here whose files we hold, read 2026-08-07

  • Reference existing artifacts by path or URLin 53 of 742, across 25 files
  • Run the full test suite after integrating changesin 51 of 742, across 19 files
  • Dispatch one agent per independent problem domainin 50 of 742, across 17 files
  • Verify fixes do not conflictin 45 of 742, across 13 files
  • Include a suggested skills section in the documentin 45 of 742, across 17 files
  • Redact sensitive informationin 41 of 742, across 11 files
  • Save to the temporary directory of the operating systemin 39 of 742, across 10 files
  • Tailor the document to user-provided focus argumentsin 39 of 742, across 9 files
  • Spot check agent changes for systematic errorsin 34 of 742, across 7 files
  • Write a handoff document summarising the current conversationin 31 of 742, across 6 files
  • Assign each agent a specific scopein 23 of 742, across 8 files
  • Provide specific scope and clear goalin 23 of 742, across 5 files

Said here and by no other author read

  • activate when work crosses sessions owners machines or gates
  • verify live state when verification is cheap
  • write the durable record using the specified order
  • use absolute paths and immutable identifiers
  • separate observed inferred and unverified claims
  • re-read the record as a cold continuation

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.