How do I install the Context Management skill?

Run npx skillmds@latest add onedro1d/context-management in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Context Management safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Context Management?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Context Management free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Context Management?

OneDro1d (@onedro1d) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Context Management by onedro1d — Agent Skill

Name: Context Management
Author: OneDro1d

Context Management

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".

OneDro1d eb81e1e 2.1 KB Updated Sep 17, 2026

File contents

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).

---name: context-managementdescription: 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".---# 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 agentSERVICE-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).

Frequently asked questions