agentleFS
Sign inStart free
maidepsmaideps/ai-harness-framework/skills/session-handoff/SKILL.md

session-handoff

Skill2 starsChanged 6 days agoMITView on GitHub

Ending a session durably — state files, traces, and a clean tree the next session can start from.

139 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use ascii-diagram, research-fleet and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • SethGammonSkill

    ascii-diagram

    Generate perfectly aligned ASCII diagrams — architecture, flow, sequence, box-and-arrow. Uses a programmatic character-grid approach so alignment is guaranteed by math, not token prediction. Includes post-render verification.

    Also in 4 projects that use this

  • SethGammonSkill

    research-fleet

    Parallel research using Fleet wave mechanics. Spawns multiple scout agents, each investigating a different angle of the same question. Findings are compressed between waves. Produces a unified research brief from multiple independent perspectives.

    Also in 3 projects that use this

  • vicoa-aiSkill

    live-preview

    Start a local app in the current user project, expose it through a tunnel, and return preview details in structured Markdown. Use when the user asks for a preview URL, public URL, shareable localhost, mobile/web preview, or tunnel setup.

    Also in 4 projects that use this

  • botlearn-aiSkill

    doc-gen

    Also in 4 projects that use this

  • flyingobsidianSkill

    terminology

    Read a codebase, find terminology, create/update definitions into a markdown document.

    Also in 3 projects that use this

  • Dizzy-TenSkill

    bug-diagnosis

    Diagnose bugs and product issues without modifying code. Use when the user explicitly invokes $bug-diagnosis or asks for diagnosis, root-cause analysis, issue classification, or fix strategy for code bugs, failing tests, configuration/dependency problems, deployment issues, performance regressions, data anomalies, or frontend/user-experience problems described through screenshots, annotations, logs, errors, or natural-language reports. Prioritize analysis and recommendations only; do not edit files.

    Also in 3 projects that use this

  • +1 more from SethGammon

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 2 are distinctive, and 6 are very specific to this project.

  • 0

    Common

    Most of the 117 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 6

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before context runs low — stop, write the handoff, commit a clean checkpoint

    line 12
  2. Distinctive:

    Before leaving a feature half-done

    line 13
  3. Very specific:

    Update session-handoff.md — current objective, completed items, verification evidence, files changed, decisions, risks, recommended next …

    line 18
  4. Very specific:

    Update docs/quality-document.md: name each feature that passed this session and rate every module touched (A/B/C/D per dimension).

    line 20
  5. Very specific:

    Update the feature's .harness/state/<id>.json with the new state (only via npm run verify-feature -- <id>).

    line 21
  6. Very specific:

    Run npm run clean-check, then commit — one logical operation per commit, message explaining WHY.

    line 23
  7. Very specific:

    If running low on context: do NOT rush — add a concise note under progress/, regenerate PROGRESS.md, and commit a clean checkpoint.

    line 28
  8. Very specific:

    Leave the repo clean enough that the next session can run ./init.sh immediately.

    line 29

“Common” is measured: kept by at least 6 in 10 of the 117 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Session Handoff

How to end a session so the next one can pick up without confusion.

When to Use

  • End of every working session
  • Before context runs low — stop, write the handoff, commit a clean checkpoint
  • Before leaving a feature half-done

Workflow

  1. Start this session's note with node scripts/framework-check.mjs progress-new "<title>" — it writes progress/NNN-YYYY-MM-DD.md with the right number, date, heading and sections, and refreshes PROGRESS.md — then fill in every section. After any later state change, regenerate the current state and index with node scripts/framework-check.mjs progress-update. PROGRESS.md is generated; do not edit its block by hand.
  2. Update session-handoff.md — current objective, completed items, verification evidence, files changed, decisions, risks, recommended next step.
  3. Record decisions in DECISIONS.md (template at the top of the file); expand long records into docs/decisions/.
  4. Update docs/quality-document.md: name each feature that passed this session and rate every module touched (A/B/C/D per dimension). npm run clean-check fails while a gate-verified feature is not mentioned.
  5. Update the feature's .harness/state/<id>.json with the new state (only via npm run verify-feature -- <id>).
  6. Record the trace: npm run session-end (merges end state, files modified, decisions, verification into the session start trace in .harness/traces/).
  7. Run npm run clean-check, then commit — one logical operation per commit, message explaining WHY.

Rules

  • State files are the source of truth, not chat history.
  • If running low on context: do NOT rush — add a concise note under progress/, regenerate PROGRESS.md, and commit a clean checkpoint.
  • Leave the repo clean enough that the next session can run ./init.sh immediately.

Quick Reference

  • Session note added and PROGRESS.md regenerated
  • session-handoff.md updated
  • DECISIONS.md updated if decisions were made
  • docs/quality-document.md updated for touched modules
  • npm run session-end recorded
  • npm run clean-check passes, committed

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free