Skip to content
Agentmart
Submit a tool

spec-handoff

Standard HANDOFF block and checkpoint files for spec-driven pipeline.

Skill by sushilti80

IndexedMIT
Write a review

Chalk Labs

Need help deploying spec-handoff?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/sushilti80-spec-handoff

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Standard HANDOFF block and checkpoint files for spec-driven pipeline. Persist to .specs/handoffs/ at gate boundaries; next agent gets paths only (Principle 8).

Use cases: data, agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/spec-handoff

What's inside

Skill name
spec-handoff
Description
Standard HANDOFF block and checkpoint files for spec-driven pipeline. Persist to .specs/handoffs/ at gate boundaries; next agent gets paths only (Principle 8).
License
MIT
Instructions
77 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Spec handoff

Every agent phase that hands off work **must** end with this block (fill all fields):

```markdown
---
## HANDOFF
**Goal completed:** [one line]

**Artifacts written:**
- [file paths, e.g. .specs/requirements/REQ-001.md]

**Key decisions:**
- [max 5 bullets]

**For next agent — paths only (do not paste this HANDOFF block):**
- Spec files to read: [paths]
- Constraints: [hard constraints — one line each, or "see spec"]
- Open risks: [paths or IDs only — not narrative]

**Blockers:** [none | list — blocks next phase if any]

**Memory updated:**
- [.agents/memory/ paths]

**Checkpoint file:**
- [.specs/handoffs/GATE-*.md or "none"]

**Human gate:** [waiting for APPROVED | APPROVED on disk | BUG ACK on disk | N/A]

**Phase:** [planning | awaiting-human | implementation | verify]

**Token profile:** [advisory | handoff | implement | docs-touch | release]

**Read order (next agent):** [max 3 paths — do not re-read chat]

**Do not carry forward:** [what is now only on disk]
---
```

## Principle 8 — persist before reset

1. Update specs and `specs-index.md` before the next agent runs
2. Write optional checkpoint: `.specs/handoffs/GATE-<slug>.md` (see playbook template)
3. Next agent prompt = **paths + recipe + phase** only — **never** paste this HANDOFF block, chat summaries, or tool logs

Orchestrator: delegation ≤500 words. Do not paste prior agent narratives or conversation summaries. Apply skill **`spec-token-budget`**. If parent chat contradicts disk, **disk wins**.

**Two-pass:** If planning is done but disk still shows DRAFT / `Human ACK: PENDING`, set **Human gate:** waiting for APPROVED and **Phase:** `awaiting-human`. Do not hand off to implementers until the user edits the file.

## Checkpoint file (orchestrator or phase owner)

Write to `.specs/handoffs/GATE-<slug>.md` at gate boundaries (recommended Tier 2+):

```markdown
# Checkpoint — [phase]
> Date: YYYY-MM-DD | Recipe: [id] | Tier: [0-3]

## Phase completed

## Spec files
- 

## Next agent / blockers

## Captured on disk (do not repeat in chat)
- 
```

## Rules

- Prefer **spec file paths** over long narrative summaries.
- Next agent reads `.specs/` as primary truth.
- If a gate is not met (e.g. REQ not APPROVED), set Blockers explicitly.
- Do not `resume` subagents across gate boundaries except same in-flight task.

From sushilti80/specforge-engineering-team, MIT.

More from sushilti80/specforge-engineering-team

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Aug 6, 2026 (2 months ago)
Last release
Aug 6, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from sushilti80

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get spec-handoff running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying spec-handoff?

CallGet help
Cite this page

spec-handoff skill. Agent Mart. https://agentmart.dev/skills/sushilti80-spec-handoff (last updated 2026-10-24)