status

A read-only project-status helper for a dossier-based workflow, with a lighter status report for small projects. A dossier is a set of project notes and task records used to track current work.

In plain words
What is it for?
Use it for session-start checks, dossier status reports, paused-work reviews, Git working-state checks, and next-step summaries.
Why use it?
It shows where the project stands, what is active or paused, and what should happen next without changing the main project files. It can also report Git state and recent commits.

Skill for Claude CodeCodex

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/raisedadead/claude-code-plugins/status
Any agent
npx skills add raisedadead/claude-code-plugins --skill status
Clone the repo
git clone --depth 1 https://github.com/raisedadead/claude-code-plugins

Made for: Claude Code, Codex.

Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,459 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00064 $0.02459
Opus 5 $0.00032 $0.01229
Sonnet 5 $0.00013 $0.00492
Haiku 4.5 $0.00006 $0.00246

Measured yesterday against content hash 2d88ef579134, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

status scanned grade B with 1 finding 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 yesterday.

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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

1. **transcripts (fallback)** — cavemem absent or empty: grep `~/.claude/projects/<project>/*.jsonl` for the most recent non-sidechain user turns plus the last assistant summary. Header `## Recovered (transcripts — cavem
plugins/dossier/skills/status/SKILL.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ds:status — the dossier driver (sit-rep)

Read-only on files; mutations route through Bash helpers. The only writes are the INDEX regen (derived, idempotent) and TaskList hydration, which projects §T into the session TaskList while §T stays source of truth.

Steps

0. Detect host env

Per ADAPTERS.md. Cache for the invocation.

1. Locate

  • .scratchpad/INDEX.md — missing → run lib-regen-index.sh to build it.
  • Enumerate ALL rows with state=live. Current dossier = the first (most-recent). state=paused rows are listed separately, outside the live set.
  • The paused set reaches the report as its own PAUSED line in step 6, printed on every full sit-rep — (none) when the set is empty. The LIGHT path exits at step 1 and never reaches it, which is correct: LIGHT runs where there is no .scratchpad/dossier/ to hold a paused wave. A paused wave that no line names is a wave nobody decides about.

No .scratchpad/dossier/ in cwd → LIGHT sit-rep, the small-work path with no ceremony:

  • git status -sb + git log --oneline -${DS_LIGHT_LOG:-5} for working state (skip git cleanly outside a repo).
  • $DS_HEALTH_CMD when set: run it and fold its output in (the operator wires a repo/rig health check; unset stays portable).
  • One block: LIGHT (no dossier): <branch> · <ahead/behind> · <N> dirty · last: <subject>, then suggest ds:new <slug> once the work grows into phases.

Exit 0 after the light sit-rep.

1a. Consolidation check

Warn (advisory, never blocking) when the tree needs tidying:

  • >1 live dossier (Vm.12): print a CONSOLIDATE block listing each live slug and its §S-tail age, then suggest picking the current one and pausing or closing the rest.
  • stale-live (Vm.13): any live dossier whose last §S entry is older than ${DS_STALE_LIVE_DAYS:-14} days → suggest pause or ds:close --abandon.
  • drift (Vm.15): an INDEX carrying a <!-- drift:N slugs:... --> trailer (any dossier rendered drift! — header/location/§Z disagreement, the sealed-zombie class) gets a DRIFT block naming each drift slug and its likely cause, then a route: a §Z-closed drift auto-heals on the next SessionStart (session-start runs lib-reconcile-state.sh); anything else is operator-resolved — finish the close (ds:close --resume) or correct the header through lib-header-state.sh, which is the supported writer (marker_guard.py exits 2 on a non-canonical token written any other way). Run hooks/lib-ds-check.sh .scratchpad for the deterministic list.

Read the full file on GitHub · 142 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. yesterday First seen · 142 lines · 64 tokens per session scan B 2d88ef579134

Subscribe to this mod's changes

status is a skill published in the GitHub repository raisedadead/claude-code-plugins (2 stars, last pushed 6d ago), licensed ISC. It adds 64 tokens to every session and 2,459 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 tokens

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…

openai/codex · 114 tokens

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…

openai/codex · 113 tokens

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…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 170 tokens