context-manager
Skill9 starsChanged 3 months agoMITView on GitHub
Use at the end of every task in a scaffolded project and whenever the session context grows heavy. Enforces the context threshold, generates the continuation prompt for the next chat, and applies context minimalism rules. Triggers on "context check", "continuation prompt", "handoff", or context warnings.
13 other projects use a version of this.
Adopted by
Most recently taken up by
- tturupapa-stack/agent-company-v5.1their own version, first seen Nov 8, 2026
- shino369/claude-code-personal-workspacetheir own version, first seen Nov 8, 2026
- Mark393295827/graph-engineering-architecturestheir own version, first seen Nov 8, 2026
- davidanthonyn/claude-skillstheir own version, first seen Oct 20, 2026
- xfstudio/skillstheir own version, first seen Oct 13, 2026
- felvieira/claude-skills-fvtheir own version, first seen Sep 2, 2026
Other versions13 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 13
- gaoziman/claude-context-manager★ 87same name
- jshsakura/awesome-opencode-skills★ 30same name
- felvieira/claude-skills-fv★ 27same name
- belokonm/claude-supercode-skills★ 11same name
- xfstudio/skills★ 9same name
- nicolasestrem/antigravity-gemini-skills★ 8same name
- Mark393295827/graph-engineering-architectures★ 4same name
- shino369/claude-code-personal-workspace★ 4same name
- ai4brands-design/claude-skills★ 2same name
- RockaRhymeLLC/claude-code-skills★ 1same name
3 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository6 other files it gives its agents.
- cortexSkill
- design-firstSkill
- persona-labSkill
- pipeline-loggerSkill
- project-scaffolderSkill
- synapseSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 10 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 23
Update wiki/handoff.md (≤80 lines): done, in progress, next, files to read.
- Very specific: line 24
Update wiki/priorities.md (≤100 lines): checkbox states current.
“Common” is measured: kept by at least 6 in 10 of the 10 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Context Manager
Overview
Keeps sessions inside a healthy context window. The wiki is long-term memory; the chat is working memory that must be renewed BEFORE quality degrades (context rot).
Core principle: hand off proactively at the threshold, never reactively at the limit.
Threshold Check (after every completed task)
- Threshold: 300k tokens by default — configurable via the "Context threshold" line in the project CLAUDE.md.
- Estimate consumption from: system context warnings, number/size of files read this session, conversation length. When in doubt, assume you are CLOSER to the threshold than you think.
- Below threshold → continue normally.
- Above threshold → no new activities. Finish the current activity if nearly done, then run the Handoff Procedure.
Handoff Procedure
- Update
wiki/handoff.md(≤80 lines): done, in progress, next, files to read. - Update
wiki/priorities.md(≤100 lines): checkbox states current. - Generate the Continuation Prompt (template below, ≤40 lines) and print it as the final message so the user can paste it into a fresh chat.
- Update
daily-log/YYYY-MM-DD.md.
Continuation Prompt Template
# Continue: {project} — Phase {N}
Read in order (nothing else):
1. CLAUDE.md
2. wiki/handoff.md
3. docs/phases/PHASE-{N}-execution.md
State: activities {list} DONE; activity {n} IN PROGRESS at {exact point}.
Next: activity {n} — {description}. VERIFY: {criterion}.
Mode: {Normal/Autopilot/Autonomous}. Context threshold: {X}k.
Do NOT re-read: {stable files already processed}.Context Minimalism Rules
Injected into every generated CLAUDE.md:
- Wrong path →
/rewind+ re-prompt with the lesson learned. Never pile inline corrections on a polluted context. - Between large tasks →
/clear+ written brief (the Execution Doc activity is the brief). /compactalways with a hint ("keep decisions and current activity state").- Inject the minimum: link wiki pages instead of pasting them; excerpts over full files.
Anti-Patterns
| Don't | Do instead |
| Push through the threshold "to finish the phase" | Hand off — the next chat finishes with fresh quality |
| Write a continuation prompt >40 lines | The wiki holds the detail; the prompt only points |
| Correct a derailed session inline for the third time | /rewind, add the lesson to the prompt, go again |
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

