aget-close-project

aget-close-project is a skill for Claude Code from aget-framework/template-advisor-aget. It costs 78 tokens per session (4,094 once invoked), scanned A, original, Apache-2.0.

A project-closure workflow for finishing a project plan. It checks evidence such as verification tests, commits, and a retrospective, then records whether the project is complete, closed, abandoned, or replaced.

In plain words
What is it for?
Use it to close a named project plan, verify its completion gates, record a reason for non-complete outcomes, and hand deferred work forward.
Why use it?
It prevents projects from being marked finished without checking their stated conditions. It also captures unfinished work for a later plan.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: names the AskUserQuestion tool; mentions AGENTS.md.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 scripts/close_gate_check.py planning/PROJECT_PLAN_<name>.md.

Good fit Use it to close a named project plan, verify its completion gates, record a reason for non-complete outcomes, and hand deferred work forward.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/aget-framework/template-advisor-aget
agentmods
npx agentmods add skills/aget-framework/template-advisor-aget/aget-close-project

Made for: Claude Code.

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 aget-close-project

README.md
[![agentmods](https://agentmods.dev/badge/skills/aget-framework/template-advisor-aget/aget-close-project/github.svg)](https://agentmods.dev/skills/aget-framework/template-advisor-aget/aget-close-project)
Your own site
<a href="https://agentmods.dev/skills/aget-framework/template-advisor-aget/aget-close-project"><img src="https://agentmods.dev/badge/skills/aget-framework/template-advisor-aget/aget-close-project/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 aget-close-project

Your own site · 80×15
<a href="https://agentmods.dev/skills/aget-framework/template-advisor-aget/aget-close-project"><img src="https://agentmods.dev/badge/skills/aget-framework/template-advisor-aget/aget-close-project.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,094 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.
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 $0.00078 $0.04094
Opus 5 $0.00039 $0.02047
Sonnet 5 $0.00016 $0.00819
Haiku 4.5 $0.00008 $0.00409

Measured 9d ago against content hash 7a93f8a5a8dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

aget-close-project 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.

.claude/skills/aget-close-project/SKILL.md · 263 lines

How it starts

The opening of the file, as written. The whole thing — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/aget-close-project

Terminally close a PROJECT_PLAN with verifiable assertion, closure checklist, and deferred-surface handoff. Strict counterpart to /aget-create-project.

Input

$ARGUMENTS — PROJECT_PLAN filename (or slug; resolved against planning/)

Mode Detection

Input Pattern Mode Behavior
Empty Interactive List candidate plans (status=IN PROGRESS or all gates [x]), prompt for selection
<filename> or <slug> Explicit Resolve to planning/PROJECT_PLAN_<name>.md; close that plan
<filename> --reason <text> Explicit with reason Required for non-COMPLETE closures (CLOSED, ABANDONED, SUPERSEDED)
<filename> --override <text> L178 override Bypasses gate-completion gate (Step 2) with recorded reason

Project Closure Process

Step 0: Scope-Fit + Identity Check

  1. Read .aget/identity.json — extract name, domain
  2. Resolve PROJECT_PLAN path; verify file exists under planning/
  3. If file absent: ERROR with candidate-list suggestion

Step 1: Input Analysis

Parse $ARGUMENTS:

  • Plan filename or slug
  • Optional --reason <text> (required for CLOSED/ABANDONED/SUPERSEDED)
  • Optional --override <text> (L178 path — bypasses Step 2 with recorded reason)

Step 2: Gate-Completion Gate (Strict — C-CLOSE-001)

Automate the scan, don't eyeball it (C-P1 guard, v3.20; L736 assert-before-verify):

python3 scripts/close_gate_check.py planning/PROJECT_PLAN_<name>.md

Exit 2 = BLOCK (unchecked conformance signals listed: Pending/In-Progress gate status, PENDING V-test rows, unchecked Closure/Finalization items). Exit 0 = clean. The script is the consumer's check (C-P4) that backs the prose criteria below — do not assert closure-readiness without running it.

REFUSE close if any of:

  • Any gate marked [ ] (unmarked) in plan body — UNLESS override path
  • Any V-test result missing for a CAP that has gates
  • Plan header **Status:** field absent or not parseable
  • close_gate_check.py exits 2 (unchecked conformance signals) — UNLESS override path

Read the full file on GitHub · 263 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 · 263 lines · 78 tokens per session scan A 7a93f8a5a8dc

Subscribe to this mod's changes

aget-close-project is a skill published in the GitHub repository aget-framework/template-advisor-aget (2 stars, last pushed 9d ago), licensed Apache-2.0. It adds 78 tokens to every session and 4,094 once invoked, about $0.0004 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 2026-08-31.