Skills cc-skill-strategic-compact

📦

cc-skill-strategic-compact

Name: cc-skill-strategic-compact
Author: affaan-m

v1.0 Content revision r1 Medium Risk ⚙️ External commands📁 Filesystem access

Manage Claude Code Compact Prompts

Long Claude Code sessions can lose focus when automatic compaction happens at awkward times. This skill provides a hook helper that suggests manual compaction at tool call milestones.

Supports: Claude Codex Code(CC)

📊 70 Adequate

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request

Review the Skillstore skill "cc-skill-strategic-compact" from https://skillstore.io/skills/sickn33-cc-skill-strategic-compact.md and its manifest at https://skillstore.io/api/skills/sickn33-cc-skill-strategic-compact/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/sickn33-cc-skill-strategic-compact.md Signed manifest GET /api/skills/sickn33-cc-skill-strategic-compact/manifest Signed lockfile GET /api/skills/sickn33-cc-skill-strategic-compact/lockfile

Test it

Using "cc-skill-strategic-compact". User asks when to compact during a long refactor.

Expected outcome:

Suggested compact points after research, before broad edits, after tests, and before switching tasks.

Using "cc-skill-strategic-compact". User wants to change reminder frequency.

Expected outcome:

Recommendation to raise or lower the threshold based on session length and tool call volume.

Using "cc-skill-strategic-compact". User reviews hook safety before enabling it.

Expected outcome:

Confirm the hook is opt-in.
Review the Bash script behavior.
Check how the temporary counter file is stored.

Security Audit

Medium Risk

v4 • 7/6/2026 Open versioned report

The skill is a small Bash hook helper that prints compact reminders during long Claude Code sessions. No prompt injection or network behavior was found, but the script executes through a hook and uses a predictable temporary counter file.

Files scanned

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (1)

Medium

suggest-compact.sh:14-18

Automatic Hook Execution Surface

The sample configuration wires the script into a PreToolUse hook for Edit and Write actions, which would run it automatically when those tools are used. The script appears benign, but marketplace installation must not silently enable this behavior.

Lines 14-18 show a command hook configuration that invokes this script on tool use. There is no malicious payload, but automatic local shell execution is a clear security surface.

Capability review items (2)

These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.

Medium

suggest-compact.sh:1

Unix shell invocation

#!/bin/bash

The skill includes a Bash script intended to run from a Claude hook, so enabling it executes local shell code in the user's environment. The observed behavior is limited, but shell execution is a real permission boundary.

Medium

suggest-compact.sh:31

Temp directory access

COUNTER_FILE="/tmp/claude-tool-count-$$"

The script stores state in /tmp using a predictable process-id based name and later reads and writes that path. Without mktemp, ownership checks, or numeric validation, a local user could tamper with the counter path.

Risk Factors

⚙️ External commands (4)

suggest-compact.sh:36 suggest-compact.sh:37 suggest-compact.sh:50 suggest-compact.sh:1

📁 Filesystem access (5)

suggest-compact.sh:11 suggest-compact.sh:18 suggest-compact.sh:11 suggest-compact.sh:18 suggest-compact.sh:31

Audited by: codex View Audit History →

Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report

Copy report link

https://skillstore.io/skills/sickn33-cc-skill-strategic-compact/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/sickn33-cc-skill-strategic-compact/security.svg)](https://skillstore.io/skills/sickn33-cc-skill-strategic-compact?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/sickn33-cc-skill-strategic-compact?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/sickn33-cc-skill-strategic-compact/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/sickn33-cc-skill-strategic-compact.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

Academic citations (APA · BibTeX · CFF)

APA citation

affaan-m. (2026). cc-skill-strategic-compact security audit report (audit version 4) [Author version 1.0]. Skillstore. https://skillstore.io/skills/sickn33-cc-skill-strategic-compact/audits/4

BibTeX citation

@techreport{affaan-m-sickn33-cc-skill-strategic-compact-2026,
  author = {affaan-m},
  title = {cc-skill-strategic-compact security audit report (audit version 4)},
  institution = {Skillstore},
  year = {2026},
  number = {4},
  url = {https://skillstore.io/skills/sickn33-cc-skill-strategic-compact/audits/4},
  note = {Author version 1.0}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "cc-skill-strategic-compact security audit report (audit version 4)"
version: "1.0"
type: report
authors:
  - name: "affaan-m"
date-released: "2026-07-06"
url: "https://skillstore.io/skills/sickn33-cc-skill-strategic-compact/audits/4"
identifiers:
  - type: other
    value: "skillstore:sickn33-cc-skill-strategic-compact:audit:4"
    description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: High

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Plan a long refactor

A developer wants reminders to compact after extended edit sessions.

Coordinate milestone handoffs

A lead uses manual compaction checkpoints before switching from research to implementation.

Tune local workflow hooks

A power user adjusts the compact threshold to match preferred session length.

Try These Prompts

Enable Basic Reminders

Help me decide whether to enable the strategic compact hook for a long Claude Code session.

Set a Threshold

Recommend a compact reminder threshold for a session that will include research, edits, and tests.

Plan Phase Checkpoints

Create compact checkpoints for my current Claude Code task: exploration, implementation, verification, and final handoff.

Audit Hook Usage

Review my planned Claude hook configuration for this skill and identify safety, reliability, and consent concerns before I enable it.

Best Practices

Enable the hook only after reviewing the script and understanding when it runs.
Set a threshold that matches your normal session length.
Treat compact reminders as prompts for judgment, not automatic workflow decisions.

Avoid

Do not enable hooks from community skills without reading their commands.
Do not rely on this helper as a substitute for task summaries.
Do not store sensitive workflow state in shared temporary locations.

Frequently Asked Questions

Does this skill run commands?

Yes. The included Bash script runs when a user configures it as a Claude hook.

Does it send data over the network?

No evidence found in the reviewed files for network requests or remote data transfer.

Does it compact automatically?

No. It prints reminders so the user can decide when to compact.

Which tools does it support?

It is marked compatible with Claude, Codex, and Claude Code, but the hook example targets Claude Code.

Can I change the reminder threshold?

Yes. Set COMPACT_THRESHOLD in the environment before running the hook.

What should I review before enabling it?

Review the Bash script, the hook trigger, and the temporary file behavior.

Developer Details

Author

affaan-m

License

MIT

Author version

v1.0

Skillstore revision

Version notice

The author-declared version is not valid SemVer.

Repository

https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/cc-skill-strategic-compact

Ref

01171b582d636c013315c5e0d969c64f8d9cdff2

Maintenance freshness

7/18/2026

Usage

6 downloads · 94 views

File structure

📄 SKILL.md

📄 suggest-compact.sh