conscientiousnessconscientiousness/herdr-pstack-orchestrator/skills/principle-guard-the-context-window/SKILL.mdprinciple-guard-the-context-window
Skill1 starsChanged 16 days agoMITView on GitHub
Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents; keep summaries in the main thread, not raw payloads.
Files
Herdr runtime
Before following the original instructions below, read the sibling pstack-herdr skill and its required mapping. Resolve relative references from this installed skill directory. Use a named sibling skill by reading ../<name>/SKILL.md, because explicit-only siblings are not in the harness skill list. The mapping translates original repository paths to bundled resources; no separate upstream checkout is needed. The Herdr mapping overrides upstream delegation tools, model defaults, setup files, and Cursor-specific capabilities. Delegate only through horch, using workers.toml. Keep workflow coordination in the controller. A bounded worker assignment remains bounded: do not start nested workers. User and project instructions take precedence. Check required capabilities before acting; keep unavailable steps unresolved. For setup-pstack, use the adapter's role setup instead of the original Cursor rule-writing procedure.
Guard the Context Window
Why: Context overflow degrades reasoning quality, creates compression artifacts, and halts progress.
Pattern:
- Size phases and cap scope. Limit files per phase, set turn budgets, account for mechanism costs.
Other versions42 projects use a version of this.
Word for word · 0
None found.
Edited · 41
- backnotprop/pstack★ 3.3k88% same
- jtaroreh/agystack★ 12825% same
- uzairansaruzi/p3-stack★ 12635% same
- dsebban/skills★ 7188% same
- Scino/fstack★ 1829% same
- kkgogogo17/pi-pstack★ 930% same
- mariusflorescu/pstack-t3★ 988% same
- creedants/pstack-t3★ 894% same
- adjohn/pstack★ 439% same
- alexnthnz/keel★ 488% same
31 more not listed
Wrote their own version · 1
- TheOnlyFusionCube/potetos-for-everyone★ 5same name
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.
Used alongsideProjects with it also use setup-pstack, make-bot-ui and 2 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
bnemaSkillsetup-pstack
Configure which Pi models pstack uses per role. Detects available provider/model specs and writes pstack's user configuration. Use for /setup-pstack, "configure pstack models", or changing pstack model choices.
Also in 21 projects that use this
Xia-AtaraxiaSkillmake-bot-ui
Builds a small web page whose buttons wake an agent over a webhook: a local server keeps the sender key server-side and POSTs JSON to a webhook-triggered routine, and the page is exposed on the existing Tailscale node. Use for \"make a bot UI\", \"a dashboard with buttons that trigger the agent\", \"wake the bot from a page\", handing a webhook sender key to the server without pasting it in chat, or putting that UI on the tailnet. Not for general frontend work - use principle-frontend; not for tailnet health or reachability - use tailscale.
Also in 15 projects that use this
ianclearySkillpoteto-help
Guides users through pstack setup, /poteto-mode, and picking the skill, playbook, or principle for a task. Type /poteto-help with a question.
Also in 8 projects that use this
jtarorehSkillpoteto-mode
poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work. Use for poteto, /poteto-mode, or requests to work in this style.
Also in 4 projects that use this
In this repository58 other files it gives its agents.
- verify-herdr-orchestratorSkill
- architectSkill
- arenaSkill
- automate-meSkill
- benchmark-checklistSkill
- blast-radiusSkill
- broSkill
- control-cliSkill
- control-uiSkill
- correctSkill
- create-formal-verification-skillSkill
- create-verification-skillSkill
- deslopSkill
- figure-it-outSkill
- herdr-orchestratorSkill
- howSkill
- interrogateSkill
- in-your-own-wordsSkill
- ketchupSkill
- maintain-formal-verification-skillSkill
- maintain-verification-skillSkill
- no-commentsSkill
- poteto-modeSkill
- principle-attack-the-premiseSkill
- principle-boundary-disciplineSkill
- principle-build-the-leverSkill
- principle-encode-lessons-in-structureSkill
- principle-exhaust-the-design-spaceSkill
- principle-experience-firstSkill
- principle-explain-the-numberSkill
- principle-fix-root-causesSkill
- principle-foundational-thinkingSkill
- principle-laziness-protocolSkill
- principle-make-operations-idempotentSkill
- principle-migrate-callers-then-delete-legacy-apisSkill
- principle-minimize-reader-loadSkill
- principle-model-the-domainSkill
- principle-never-block-on-the-humanSkill
- principle-outcome-oriented-executionSkill
- principle-prove-it-worksSkill
- principle-redesign-from-first-principlesSkill
- principle-separate-before-serializing-shared-stateSkill
- principle-sequence-verifiable-unitsSkill
- principle-subtract-before-you-addSkill
- principle-test-behavior-not-implementationSkill
- principle-type-system-disciplineSkill
- pstack-herdrSkill
- recallSkill
- reflectSkill
- sharpenSkill
- show-me-your-workSkill
- swarmSkill
- tddSkill
- teachSkill
- technical-writingSkill
- typescript-best-practicesSkill
- unslopSkill
- whySkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.