Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Context Management

ASecurity

Maintain and compress the context store so analysis is done once and reused, never repeated. Use to record a confirmed root cause, an architecture decision, or a service/contract change; or to compress sprawling notes back into the terse store. Triggers on "remember this", "update the context", "record decision", "we already analyzed this", "compress".

3 stars
0 votes
0 copies
0 views
Added 9/24/2026
ai-agentsrustgogit

Security Analysis

A100/100

Scanned 9/24/2026

$npx -y skills add OneDro1d/dark-factory --skill context-management --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Context Management?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Context Management
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/onedro1d-context-management/badge)](https://www.skillsdirectory.com/skills/onedro1d-context-management)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: context-management
description: Maintain and compress the context store so analysis is done once and reused, never repeated. Use to record a confirmed root cause, an architecture decision, or a service/contract change; or to compress sprawling notes back into the terse store. Triggers on "remember this", "update the context", "record decision", "we already analyzed this", "compress".
allowed-tools: Read, Write, Edit, Grep, Glob
---

# Context Management (analyze once, reuse forever)

Goal: keep `.claude/context/` the single, terse, trustworthy memory so agents never re-scan the repo to re-learn what's known. This is the main token-saving lever.

## The store
- `SERVICE-MAP.md` — components + flows (one line each).
- `FINDINGS.md` — confirmed bugs/root causes (append-only ledger, status-tagged).
- `DECISIONS.md` — architecture decisions/rulings (ADR log).
- `<service>/CLAUDE.md` — deep per-service detail.
- shared-models `CLAUDE.md` — contract index.

## When to write
- **Confirmed root cause** → new `F-###` in FINDINGS.md (symptom, cause, `file:line`, status). So it's never re-investigated.
- **Design/architecture decision** → new `D-###` in DECISIONS.md (decision, why, source).
- **New/changed service, routing key, table, object-store key** → update SERVICE-MAP.md + the service CLAUDE.md + (if a contract) the shared-models index.
- **Status change** (OPEN→FIXED) → update the existing entry, don't duplicate.

## How to write (compression rules)
- One fact per entry. Cite a source (`file:line`, ruling, ticket) for every claim — no guessing.
- Prefer tables/IDs over prose. Replace, don't append, when a fact changes.
- If notes have grown long, distill to the durable fact and delete the scratch.
- Keep each context file roughly a screen — if it's growing, compress.

## Read-first reminder for every agent
SERVICE-MAP → FINDINGS → DECISIONS → the one relevant CLAUDE.md → source. Stop as soon as you have enough.

## Don't
- Don't record session chatter or anything the code/git already states.
- Don't let the store drift from code — if you find a stale entry, fix it (cite the code).

Attribution

OneDro1dOneDro1d
View sourceSee grades on GitHubMore from OneDro1d →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →