done

A task-completion workflow for MASTER_PLAN.md projects. It guides an agent through checking changes, optionally running tests, updating the plan, committing, and pushing finished work.

In plain words
What is it for?
Reviewing modified files, running the appropriate test command, recording a completion summary, updating the task plan, and shipping the result.
Why use it?
It collects the information needed to close a task and provides a repeatable final check before changes are shared.

Skill for Claude CodeCodex

Part of the master-plan plugin — 4 skills shipped together

Install

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.

agentmods
npx agentmods add skills/endlessblink/master-plan/done
Any agent
npx skills add endlessblink/master-plan --skill done
Clone the repo
git clone --depth 1 https://github.com/endlessblink/master-plan

Made for: Claude Code, Codex.

Or install master-plan, the plugin that ships this one along with the rest of its 4 skills.

Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,239 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00052 $0.01239
Opus 5 $0.00026 $0.00620
Sonnet 5 $0.00010 $0.00248
Haiku 4.5 $0.00005 $0.00124

Measured 3d ago against content hash 66c20d15a772, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

done 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 3d 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.

skills/done/SKILL.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task Completion Workflow

Finalize a completed task: verify tests pass, commit changes, update MASTER_PLAN.md, and push.

Triggers

  • /master-plan:done - Main command
  • "mark done", "task complete", "finish task", "ship it"

Workflow

Step 1: Check What Changed

Run git status to see what files were modified:

git status
git diff --stat

Output immediately:

Files changed:
- [list of modified files]

Step 2: Get Task Information

Use AskUserQuestion to collect:

  1. Task ID (header: "Task ID")

    • Options: "Tracked task (enter ID)" or "Quick fix (no task ID)"
  2. Run tests? (header: "Tests")

    • Options: "Yes — run test suite (Recommended)" or "Skip tests"

Then ask in plain text: "What's a brief summary of the changes? (1-2 sentences)"

IMPORTANT: Wait for user to provide the summary before proceeding.

Step 3: Run Tests (unless skipped)

Detect and run the project's test command. Check in order:

  1. If package.json exists → npm test
  2. If Cargo.toml exists → cargo test
  3. If pyproject.toml or setup.py exists → pytest
  4. If Makefile with test target → make test
  5. If go.mod exists → go test ./...

If tests fail: STOP immediately. Report failures. Do NOT proceed. If tests pass: Continue. If no test command found: Warn user and continue.

Step 4: Update MASTER_PLAN.md (if tracked task)

Skip this step if user selected "Quick fix (no task ID)".

CRITICAL: Tasks may appear in multiple locations. Update ALL of them:

4a. Summary/Roadmap Table

Find the task row and update:

# Before:
| **TASK-XXX** | **Title** | **P2** | PLANNED | ... |

# After:
| ~~**TASK-XXX**~~ | ✅ **Title** | **P2** | ✅ DONE (YYYY-MM-DD) | ... |
4b. Subtask/Bullet Lists
# Before:
- TASK-XXX: Description

# After:
- ~~TASK-XXX~~: ✅ Description
4c. Detailed Section Header
# Before:
### TASK-XXX: Title (IN PROGRESS)

# After:
### ~~TASK-XXX~~: Title (✅ DONE)

Read the full file on GitHub · 184 lines

Changes

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.

  1. 3d ago First seen · 184 lines · 52 tokens per session scan A 66c20d15a772

Subscribe to this mod's changes

done is a skill published in the GitHub repository endlessblink/master-plan (27 stars, last pushed 6mo ago), licensed MIT. It adds 52 tokens to every session and 1,239 once invoked, about $0.0003 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 2026-08-30.