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.
npx agentmods add skills/groupzer0/vs-code-agents/document-lifecyclenpx skills add groupzer0/vs-code-agents --skill document-lifecyclegit clone --depth 1 https://github.com/groupzer0/vs-code-agentsWhat 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 | $0.00032 | $0.01254 |
| Opus 5 | $0.00016 | $0.00627 |
| Sonnet 5 | $0.00006 | $0.00251 |
| Haiku 4.5 | $0.00003 | $0.00125 |
Grade A, and why
document-lifecycle 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 2d 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Document Lifecycle Skill
Manages document state transitions, unified numbering, and automated closure across all agent-output directories.
Core Principle
Every work chain shares a single ID. When Analyst creates analysis 080, the downstream plan, implementation, QA, UAT, and critique all use ID 080. This enables human traceability across the entire lifecycle.
Documents in terminal status belong in closed/ subfolders. Active work stays visible; completed work is archived but accessible.
Terminal Statuses
These statuses trigger document closure (move to closed/):
| Status | Meaning | Closed By |
|---|---|---|
Committed |
Changes committed to git (awaiting release) | DevOps |
Released |
Successfully pushed/published | DevOps |
Abandoned |
Explicitly dropped, will not proceed | User (manual) |
Deferred |
Postponed indefinitely | User (manual) |
Superseded |
Replaced by a newer document | User (manual) |
Resolved |
All findings addressed (critiques only) | Critic |
Unified Numbering Protocol
The .next-id File
Location: agent-output/.next-id
Contents: Single integer (e.g., 081)
Rules:
- Only originating agents (Analyst, Planner when no analysis) read and increment
- Downstream agents inherit the ID from their source document
- Never skip numbers; always use the next available
Document Header Format
Every document in agent-output/ MUST include:
---
ID: 080 # Global sequence number
Origin: 080 # Chain origin (same as ID for originating docs)
UUID: a3f7c2b1 # 8-char random hex for collision-proofing
Status: Active # Current lifecycle state
---
ID Assignment Rules
| Scenario | Action |
|---|---|
| Analyst starts new investigation | Read .next-id, increment, use as ID, write back |
| Planner creates plan from analysis | Inherit ID/Origin from analysis doc |
| Planner creates plan from user request (no analysis) | Read .next-id, increment, use as ID, write back |
| Implementer/QA/UAT/Critic work on plan | Inherit ID/Origin from plan doc |
| Retrospective reviews plan | Inherit ID/Origin from plan doc |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 166 lines · 32 tokens per session scan A 189a9509b6bd
document-lifecycle is a skill published in the GitHub repository groupzer0/vs-code-agents (284 stars, last pushed 7mo ago), licensed MIT. It adds 32 tokens to every session and 1,254 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…