context-management SKILL.md skillA

context-management from brunob54/superpowers-orchestrator is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add brunob54/superpowers-orchestrator/context-management@git:20261008.473e04a

Pins git:20261008.473e04a in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
brunob54/superpowers-orchestrator
Path
skills/context-management/SKILL.md
Versions recorded
13
Latest version
git:20261008.473e04a, committed Oct 8, 2026
First version recorded
Apr 3, 2026
Size
17,806 bytes
Repository stars
3
License
MIT

Use in long or noisy sessions to persist durable state across session boundaries via state.md. Also generates project-map.md when asked to map the project. Triggers on: user explicitly asks to "save state", "compress context", "map this project", "generate project map", "create project map", "archive the session log", cross-session handoff needed, or repeated failures indicate context is getting stale.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Context Management

## Route first — read this before anything else

| User said | Go to |
|---|---|
| "map this project" / "generate project map" / "create project map" / "update project map" | [Project Map](#project-map) section |
| "save state" / "compress context" / session ending with ongoing work | [Procedure](#procedure) section |
| "archive the session log" | [session-log.md Format and Maintenance](#session-logmd-format-and-maintenance) section |
| Starting a task on a project with existing history | Grep `session-log.md` first, then proceed |

Do not default to `state.md` for a map request. Do not default to `project-map.md` for a save-state request.

---

## Purpose

Claude Code automatically compresses context within a session. This skill has two complementary responsibilities:

1. **Cross-session persistence** — `state.md` preserves decisions and progress for the *current task* when a session ends mid-work.
2. **Accumulated project memory** — `session-log.md` builds a searchable history of decisions, rejected approaches, and hard-won facts across sessions. Written manually via this skill — only when there is something worth preserving.

## When to Use
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add brunob54/superpowers-orchestrator/context-management@sha256:cb8d69596b54ae5e

The line at the top of this page pins the label git:20261008.473e04a, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_rz77nfxcp6e3qnb5.svg)](https://markdownregistry.com/a/art_rz77nfxcp6e3qnb5)

5 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 13 versions of this file, between Apr 3, 2026 and Oct 8, 2026, about one every 16 days.

versioncommittedcommitsizeaudit
git:20261008.473e04a latest2026-10-08 473e04a 17,806 BA view · diff
git:20261008.af66b1e2026-10-08 af66b1e 17,731 BA view · diff
git:20261008.606e0f72026-10-08 606e0f7 17,660 BA view · diff
git:20261008.19845fe2026-10-08 19845fe 17,643 BA view · diff
git:20261008.bfac4122026-10-08 bfac412 17,260 BA view · diff
git:20261004.5129deb2026-10-04 5129deb 14,592 BA view · diff
git:20260920.77a250a2026-09-20 77a250a 14,609 BA view · diff
git:20260920.0bd214e2026-09-20 0bd214e 14,168 BA view · diff
git:20260825.1f826712026-08-25 1f82671 11,528 BA view · diff
git:20260415.0a78a702026-04-15 0a78a70 11,462 BA view · diff
git:20260411.901ba622026-04-11 901ba62 10,308 BA view · diff
git:20260407.5b919bb2026-04-07 5b919bb 9,882 BA view · diff
git:20260403.fdd0bfe2026-04-03 fdd0bfe 8,448 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (17806 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

brunob54/superpowers-orchestrator · 3 stars · license MIT · pushed 2026-10-26 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_rz77nfxcp6e3qnb5
GET https://markdownregistry.com/api/v1/resolve?ref=brunob54/superpowers-orchestrator/context-management
GET https://markdownregistry.com/api/v1/blob/cb8d69596b54ae5ee371270f170da9d0fe4d16e161cbcb9f7e257c76cdeabb6a

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from brunob54/superpowers-orchestrator

brainstorming SKILL.md skill
brunob54/superpowers-orchestrator · skills/brainstorming/SKILL.md · MUST USE when the user wants new features, behavior changes, refactoring with new capabilities, or architecture…
git:20260921.cf1d92c · audit A · 3 stars
claude-md-creator SKILL.md skill
brunob54/superpowers-orchestrator · skills/claude-md-creator/SKILL.md · Creates minimal, high-signal CLAUDE.md and AGENTS.md context files based on empirical best practices. Invoke on /init…
git:20260328.a951826 · audit A · 3 stars
dashboard SKILL.md skill
brunob54/superpowers-orchestrator · skills/dashboard/SKILL.md · Shows the status of this repository on a claude.ai Artifact page — unfinished orchestration runs, branches, work logs…
git:20261025.5ed9039 · audit A · 3 stars
deliberation SKILL.md skill
brunob54/superpowers-orchestrator · skills/deliberation/SKILL.md · Use BEFORE brainstorming when facing a complex architectural, technology, or design decision where the options are not…
git:20260415.0a78a70 · audit A · 3 stars
dependency-management SKILL.md skill
brunob54/superpowers-orchestrator · skills/dependency-management/SKILL.md · MUST USE when updating, migrating, or auditing project dependencies: upgrading packages, fixing security…
git:20260508.ae16bf3 · audit A · 3 stars
dispatching-parallel-agents SKILL.md skill
brunob54/superpowers-orchestrator · skills/dispatching-parallel-agents/SKILL.md · Use when 2+ tasks are independent and can run concurrently without file or state conflicts or sequential dependencies…
git:20260815.dcd9fd0 · audit A · 3 stars
error-recovery SKILL.md skill
brunob54/superpowers-orchestrator · skills/error-recovery/SKILL.md · Maintains a project-specific known-issues.md mapping recurring errors to their solutions. Consulted automatically by…
git:20260313.623081f · audit A · 3 stars
executing-plans SKILL.md skill
brunob54/superpowers-orchestrator · skills/executing-plans/SKILL.md · MUST USE when a plan.md exists and implementation needs to begin. Executes in controlled batches with verification…
git:20260817.e70e480 · audit A · 3 stars
finishing-a-development-branch SKILL.md skill
brunob54/superpowers-orchestrator · skills/finishing-a-development-branch/SKILL.md · MUST USE when implementation is verified and you need to choose the branch outcome: merge, PR, keep, or discard…
git:20261005.8280e38 · audit A · 3 stars
frontend-design SKILL.md skill
brunob54/superpowers-orchestrator · skills/frontend-design/SKILL.md · MUST USE for any frontend, UI, or web interface implementation. Enforces production-grade visual quality…
git:20260508.ae16bf3 · audit A · 3 stars
handoff SKILL.md skill
brunob54/superpowers-orchestrator · skills/handoff/SKILL.md · Write a continuation prompt for a fresh session into tmp/docs/<date>-handoff-<slug>.md, save state, and print the…
git:20260915.87c8587 · audit A · 3 stars
multi-code-review SKILL.md skill
brunob54/superpowers-orchestrator · skills/multi-code-review/SKILL.md · MUST USE when a branch needs N independent whole-branch code review rounds with fixes applied between rounds. M…
git:20261025.d9814d5 · audit A · 3 stars

Every file in brunob54/superpowers-orchestrator

Other files named context-management

context-management SKILL.md skill
a5c-ai/babysitter · library/methodologies/ccpm/skills/context-management/SKILL.md
git:20260601.da7723a · audit C · 1,891 stars
context-management SKILL.md skill
jnpiyush/agentx · .github/skills/ai-systems/context-management/SKILL.md · Manage LLM context windows efficiently. Use when implementing context compaction, conversation summarization, token…
v1.0.0 · audit A · 18 stars
context-management SKILL.md skill
rysweet/amplihack-rs · amplifier-bundle/skills/context-management/SKILL.md · Proactive context window management via token monitoring, intelligent extraction, and selective rehydration. Features…
v3.1.0 · audit A · 13 stars
context-management SKILL.md skill
rysweet/amplihack-rs · docs/claude/skills/context_management/SKILL.md · Proactive context window management via token monitoring, intelligent extraction, and selective rehydration. Use when…
v2.0.0 · audit A · 13 stars

Browse by kind, by grade A, or by owner.