compact-plus

compact-plus is a skill for Claude Code from Marcel-Bich/marcel-bich-claude-marketplace. It costs 164 tokens per session (2,266 once invoked), scanned B, original, MIT.

A procedure that saves approved work and handoff details to files before a conversation is shortened by context compaction. It also commits and pushes the tracked work product to the correct repository.

In plain words
What is it for?
Use it before context compaction when the user has approved work that must survive into a later session; it does not perform the compaction itself.
Why use it?
It preserves decisions and progress that might otherwise be lost or changed when earlier conversation details are compressed.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: reads .claude/ paths; mentions subagents.

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 credo plugin — 26 skills, 15 commands, 6 hooks shipped together

Good fit Use it before context compaction when the user has approved work that must survive into a later session; it does not perform the compaction itself.

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 Marcel-Bich/marcel-bich-claude-marketplace
Claude Code
/plugin install credo

Made for: Claude Code.

Or install credo, the plugin that ships this one along with the rest of its 26 skills, 15 commands, 6 hooks.

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 compact-plus

README.md
[![agentmods](https://agentmods.dev/badge/skills/marcel-bich/marcel-bich-claude-marketplace/compact-plus/github.svg)](https://agentmods.dev/skills/marcel-bich/marcel-bich-claude-marketplace/compact-plus)
Your own site
<a href="https://agentmods.dev/skills/marcel-bich/marcel-bich-claude-marketplace/compact-plus"><img src="https://agentmods.dev/badge/skills/marcel-bich/marcel-bich-claude-marketplace/compact-plus/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 compact-plus

Your own site · 80×15
<a href="https://agentmods.dev/skills/marcel-bich/marcel-bich-claude-marketplace/compact-plus"><img src="https://agentmods.dev/badge/skills/marcel-bich/marcel-bich-claude-marketplace/compact-plus.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 164 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,266 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00164 $0.02266
Opus 5 $0.00082 $0.01133
Sonnet 5 $0.00033 $0.00453
Haiku 4.5 $0.00016 $0.00227

Measured 11d ago against content hash b4450d4568b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade B, and why

compact-plus 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 11d 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.

Reads agent configuration directoriesmediumAgent snooping

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

`/credo:setup` offers to set these in `~/.claude/settings.json` for you (Step 9) when the
plugins/credo/skills/compact-plus/SKILL.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

compact-plus - secure progress before a compact

A standard /compact thins the conversation summary. Anything that lives only in the chat or in volatile task metadata can be lost or quietly altered when that happens. compact-plus is the ritual that runs BEFORE a /compact so nothing approved is lost: it secures the user's approved work and requirements into durable files, then confirms it is safe to compact.

This skill only SECURES. It never calls /compact itself. Securing and compacting are two separate acts: compact-plus makes the later compact (manual or automatic) safe.

When this runs

Exactly two triggers, never a third:

  1. The limit plugin injects an ACTION line naming this skill, because the session context fill crossed a configured threshold. Run it then.
  2. The user invokes it manually.

Do NOT run this on your own initiative. The model must never decide by itself that now is a good time to secure and then start the checklist unprompted - that burns tokens on every turn. Wait for the hook ACTION line or a manual invocation. This is a hard rule.

The auto-run trigger (session context, not budget)

The trigger axis is the SESSION CONTEXT fill percentage - how full the current context window is - which is the axis a /compact acts on. Keep it separate from the two budget axes (the 5 hour API limit and the weekly API limit); those are handled by the credo budget skill and never trigger this one.

credo does not ship its own hook for this. The limit plugin already provides the exact mechanism: its inject hook reads the canonical session-context fill from the statusline cache and, at each configured threshold, injects an ACTION line telling the agent to run a named skill. That hook is deterministic:

  • Each threshold fires EXACTLY ONCE per session (the crossed thresholds are recorded).
  • The fired thresholds reset only after the fill actually drops back below them, which is what a real compact does - so after a genuine compact the same threshold can fire again later. It does not re-fire on every prompt in between.

Read the full file on GitHub · 184 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. 11d ago First seen · 184 lines · 164 tokens per session scan B b4450d4568b1

Subscribe to this mod's changes

compact-plus is a skill published in the GitHub repository Marcel-Bich/marcel-bich-claude-marketplace (13 stars, last pushed yesterday), licensed MIT. It adds 164 tokens to every session and 2,266 once invoked, about $0.0008 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 2026-08-30.