agentplane-task-closure-recovery

agentplane-task-closure-recovery is a skill for Claude Code, Codex from basilisk-labs/agentplane. It costs 46 tokens per session (731 once invoked), scanned A, original, MIT.

A guide for recovering when an Agentplane task does not close correctly. Agentplane is a task and code-review workflow that tracks task state, branches, commits, and pull requests.

In plain words
What is it for?
Use it when task finishing, integration, hosted closure, pull-request creation, or branch cleanup fails or leaves conflicting artifacts.
Why use it?
A task can be finished locally while its branch, generated files, or pull request still disagree with the recorded state. The guide helps identify and resolve those mismatches.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when task finishing, integration, hosted closure, pull-request creation, or branch cleanup fails or leaves conflicting artifacts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/basilisk-labs/agentplane/agentplane-task-closure-recovery
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.

Any agent
npx skills add basilisk-labs/agentplane --skill agentplane-task-closure-recovery
Clone the repo
git clone --depth 1 https://github.com/basilisk-labs/agentplane

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for agentplane-task-closure-recovery

README.md
[![agentmods](https://agentmods.dev/badge/skills/basilisk-labs/agentplane/agentplane-task-closure-recovery/github.svg)](https://agentmods.dev/skills/basilisk-labs/agentplane/agentplane-task-closure-recovery)
Your own site
<a href="https://agentmods.dev/skills/basilisk-labs/agentplane/agentplane-task-closure-recovery"><img src="https://agentmods.dev/badge/skills/basilisk-labs/agentplane/agentplane-task-closure-recovery/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.

agentmods 80×15 button for agentplane-task-closure-recovery

Your own site · 80×15
<a href="https://agentmods.dev/skills/basilisk-labs/agentplane/agentplane-task-closure-recovery"><img src="https://agentmods.dev/badge/skills/basilisk-labs/agentplane/agentplane-task-closure-recovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 731 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00046 $0.00731
Opus 5 $0.00023 $0.00365
Sonnet 5 $0.00009 $0.00146
Haiku 4.5 $0.00005 $0.00073

Measured 9d ago against content hash 648cbb47d1f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

agentplane-task-closure-recovery 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 9d 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/agentplane-task-closure-recovery/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agentplane Task Closure Recovery

Use This Skill When

  • agentplane finish, integrate, task hosted-close, or task hosted-close-pr fails.
  • A task-close/* PR is duplicated, closed, obsolete, or still open after hosted closure.
  • pr open fails because the remote branch already exists.
  • A task is DONE locally but artifacts, branch state, or hosted closure disagree.
  • Direct-mode finish is blocked by unrelated dirty task artifacts.

First Classification

  1. Read workflow mode:
agentplane config show
  1. Identify the task state:
agentplane task show <task-id>
agentplane task verify-show <task-id>
git status --short --untracked-files=no
git rev-parse --abbrev-ref HEAD
  1. Query incident advice:
agentplane incidents advise <task-id>

Direct Mode

Expected close path:

agentplane verify <task-id> --ok --by CODER --note "..."
agentplane finish <task-id> --author CODER --body "Verified: ..." --result "..." --commit <git-rev>

If finish is blocked:

  • Check whether dirty files belong to the active task or another active task.
  • Check whether policy/incident mirrors were generated by finish and need allowed staging.
  • Do not manually edit .agentplane/tasks.json.
  • Do not use branch_pr close-tail commands in direct mode.

Branch PR Mode

Classify before recovery:

  • Implementation PR branch: task/<task-id>/<slug>
  • Closure PR branch: task-close/<task-id>/<sha>
  • Base-side closure already landed: task README has DONE status and close commit exists on main.

Useful commands:

gh pr list --state all --head "task-close/<task-id>/<sha>"
gh pr view <number> --json state,mergedAt,headRefName,baseRefName,url
git ls-remote --heads origin "task/<task-id>/*"
git ls-remote --heads origin "task-close/<task-id>/*"

Known Recovery Patterns

Remote Branch Already Exists

If pr open fails after trying to push:

  1. Compare local branch tip to the remote branch tip.
  2. If they match, continue PR creation instead of forcing another push.
  3. If they differ, stop and classify divergence before overwriting anything.

Read the full file on GitHub · 109 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. 9d ago First seen · 109 lines · 46 tokens per session scan A 648cbb47d1f8

Subscribe to this mod's changes

agentplane-task-closure-recovery is a skill published in the GitHub repository basilisk-labs/agentplane (76 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 731 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

argot-setup

Set argot up for a repository end to end — audit its history, decide what should shape its voice, fit, verify the fit actually catches things, tune the rules its own history says are noisy, and wire the places it runs (pre-write hook, pre-commit, MCP, CI). One sitting, one decision at a time, each proposed with the…

get-tmonier/argot · 129 tokens

detect-task

Internal skill for commands. Detect the active task (any tracker adapter) from the task-state file / git branch name. Do not trigger on user conversation - only when commands need task detection.

restarter/lets-workflow · 41 tokens

dos-verify-done-claims

Before accepting an agent's 'done / shipped / fixed' claim, verify it against ground truth (git ancestry + the commit's own diff) using the DOS kernel's dos verify and dos commit-audit — never the agent's own narration.

anthony-chaudhary/dos-kernel · 61 tokens

loop-bb-pr

A command that prepares a repeating check for a Bitbucket pull request. A pull request is a request to review and merge code changes into a project.

restarter/lets-workflow · 118 tokens

take-task

A workflow for claiming a tracker task and preparing the development branch for it. It verifies the task, marks it as in progress, checks for uncommitted changes, and handles branch setup according to the task state.

restarter/lets-workflow · 76 tokens

session-boundary

Internal skill for commands. Resolve and VALIDATE this branch's session boundary - the ref a session's commit range is measured from - and report how much it can be trusted. Do not trigger on user conversation; only when a command needs the session range.

restarter/lets-workflow · 55 tokens