close

close is a skill for Claude Code from raisedadead/claude-code-plugins. It costs 52 tokens per session (1,245 once invoked), scanned A, original, ISC.

A command for closing and archiving a live project dossier, meaning a structured record of a work phase. It supports completing the phase, handing off to a successor phase, or abandoning it with a recorded reason.

In plain words
What is it for?
It helps close completed work, transfer unfinished work to a named successor dossier, or archive deprioritised or superseded work with an explanation.
Why use it?
It provides a controlled way to finish or stop a phase while preserving its status and audit history.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the dossier plugin — 8 skills, 2 agents shipped together

Good fit It helps close completed work, transfer unfinished work to a named successor dossier, or archive deprioritised or superseded work with an explanation.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add raisedadead/claude-code-plugins
Claude Code
/plugin install dossier

Made for: Claude Code.

Or install dossier, the plugin that ships this one along with the rest of its 8 skills, 2 agents.

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 close

README.md
[![agentmods](https://agentmods.dev/badge/skills/raisedadead/claude-code-plugins/close/github.svg)](https://agentmods.dev/skills/raisedadead/claude-code-plugins/close)
Your own site
<a href="https://agentmods.dev/skills/raisedadead/claude-code-plugins/close"><img src="https://agentmods.dev/badge/skills/raisedadead/claude-code-plugins/close/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 close

Your own site · 80×15
<a href="https://agentmods.dev/skills/raisedadead/claude-code-plugins/close"><img src="https://agentmods.dev/badge/skills/raisedadead/claude-code-plugins/close.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,245 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 $0.00052 $0.01245
Opus 5.5 $0.00021 $0.00498
Sonnet 5.5 $0.00010 $0.00249
Haiku 4.5 $0.00005 $0.00125

Measured 7d ago against content hash 7db94f8b77d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

close 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 7d 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.

plugins/dossier/skills/close/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ds:close — plan, show, run

ds close is the close. It runs the checks, the contract converge, the §Z write, the header flip, the archive move, the contract retire commit, the INDEX regen and the lock, and it writes a §S checkpoint after each step. This page picks the mode, shows the plan to the operator and runs it.

Modes

flag use when
--complete every row is x, or each open row is carried
--successor <slug> the work continues in wave <slug>; carried rows go to its §T
--abandon "<reason>" the wave stops unfinished; open rows and bugs stay as they are
--carry T<n>,... a who=H row or a row with a T<n>+<k>d need runs after close

--carry writes the rows to the §Z after: line (FORMAT.md §12). With --successor it also copies them into the successor §T, each with a (from <slug> T<n>) note. ds progress lists the after: rows of a wave closed in the last 30 days.

Steps

1. Plan

"${CLAUDE_PLUGIN_ROOT}"/cli/ds close <wave> <mode> [--carry T<n>,...] --plan

--plan writes nothing. Exit 0 prints ready; exit 1 prints refused. One finding per line:

mark meaning
✗ blocks the run — an open row, an uncited x row, an open bug, a lock
✓ the contract converged
⚠ advisory — an unpushed repo, an accepted unmet criterion, CHANGELOG
· no contract, so converge did not run
↷ a row this close carries

The last line before the verdict names the steps still to run.

2. Show

Put the plan in front of the operator, with a one-line --summary proposal. Resolve each ✗ before the run:

Read the full file on GitHub · 84 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. 7d ago Changed · -115 lines · -6 tokens per session 7db94f8b77d7
  2. 14d ago Changed b4b340de9a0f
  3. 18d ago Changed · -2 lines 565e09974773
  4. 1mo ago Changed c3a416fdda3f
  5. 1mo ago First seen · 201 lines · 58 tokens per session scan A 0e9218d7f37c

Subscribe to this mod's changes

close is a skill published in the GitHub repository raisedadead/claude-code-plugins (3 stars, last pushed today), licensed ISC. It adds 52 tokens to every session and 1,245 once invoked, about $0.0002 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 2026-09-04.