Borrowing it
Nothing to install: this file belongs to aget-framework/aget. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/aget-framework/aget/main/.claude/skills/aget-close-project/SKILL.mdgit clone --depth 1 https://github.com/aget-framework/agetWrote 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.
[](https://agentmods.dev/skills/aget-framework/aget/aget-close-project)<a href="https://agentmods.dev/skills/aget-framework/aget/aget-close-project"><img src="https://agentmods.dev/badge/skills/aget-framework/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.
<a href="https://agentmods.dev/skills/aget-framework/aget/aget-close-project"><img src="https://agentmods.dev/badge/skills/aget-framework/aget/aget-close-project.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 51 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00078 | $0.07409 |
| Opus 5.5 | $0.00031 | $0.02964 |
| Sonnet 5.5 | $0.00016 | $0.01482 |
| Haiku 4.5 | $0.00008 | $0.00741 |
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 15d 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.
How it starts
The opening of the file, as written. The whole thing — 442 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/) plus required
--disposition <Complete|Closed|CLOSED-PARTIAL|Abandoned|Superseded>
Mode Detection
| Input Pattern | Mode | Behavior |
|---|---|---|
| Empty | Interactive | List candidate plans (status=IN PROGRESS or all gates [x]), prompt for selection |
<filename> --disposition Complete |
Explicit | Resolve the plan and attempt a complete close |
<filename> --disposition <Closed|CLOSED-PARTIAL|Abandoned|Superseded> --reason <text> |
Explicit with reason | Required for every reasoned disposition; the reason explains but never selects the disposition |
<filename> --override <text> |
L178 override | Bypasses the ENTRY gate (Step 2) with recorded reason. Scoped deliberately: it does NOT bypass either arm of the Step 4.5 EXIT gate (4.5a completeness, 4.5b accounting). Before the gh#2250 reorder this flag was the routine way to close an honest plan — every closer-authored checklist row tripped Step 2 — which converted an exception route into the only route. It is exceptional again; a close needing it for closure-row reasons is now a defect report |
Project Closure Process
Step 0: Scope-Fit + Identity Check
- Read
.aget/identity.json— extractname,domain - Resolve PROJECT_PLAN path; verify file exists under
planning/ - If file absent: ERROR with candidate-list suggestion
Step 1: Input Analysis
Parse $ARGUMENTS:
- Plan filename or slug
- Required
--disposition <Complete|Closed|CLOSED-PARTIAL|Abandoned|Superseded>; no default - Optional
--reason <text>(required for Closed/Closed (Partial)/Abandoned/Superseded); reason text explains the explicit selection and SHALL NOT infer or select it - Optional
--override <text>(L178 path — bypasses the Step 2 ENTRY gate with recorded reason; does NOT bypass Step 4.5a or 4.5b)
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.
- 15d ago Changed · +6 lines 6589a59ab2bd
- 1mo ago First seen · 436 lines · 78 tokens per session scan A 8ee20d6e7a52
aget-close-project is a skill published in the GitHub repository aget-framework/aget (12 stars, last pushed 7d ago), licensed Apache-2.0. It adds 78 tokens to every session and 7,409 once invoked, about $0.0003 per session on Opus 5.5. 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.
Other skills, from other repositories
aget-close-project
Close a PROJECTPLAN with verifiable-assertion gate (V-tests + commits + retrospective), deferred-surface scan for next-plan handoff, and status transition (ACTIVE → COMPLETE / CLOSED / ABANDONED / SUPERSEDED). Strict counterpart to /aget-create-project (D71 Layer 2). Closes asymmetric verb-pair gap at PROJECTPLAN…
aget-file-issue
File issues with L520 governance compliance.
aget-create-initiative
Scaffold approved initiative manifests at planning/initiatives/INIT-.md. Mirrors /aget-create-project STRICT (D71 Layer 2) — direct Write/Edit to planning/initiatives/ is PROHIBITED once this skill is invoked. Implements SOPinitiative.md (graduated procedure) + future AGETINITIATIVESPEC. Consumes PROPOSALinit.md…
aget-create-project
Create research projects with context-aware scaffolding. Reads AGET identity, searches prior work, pre-populates Due Diligence. Use when starting any formal AGET project.
aget-check-initiative
Read-only cross-system coherence check for initiatives. Aggregates state from KB, GitHub, Linear, and Slack, then reports alignment and drift.
aget-review-project
Mid-flight review of active project plans. Assesses gate progress, V-test completion, blockers, and recommendations. Use to evaluate project health.