token-budget
Skill2 starsChanged 5 months agoMITView on GitHub
Per-session token discipline — cache, delegate, compact. Use when output is getting verbose, context is filling, or cache hit-rate drops. Companion to context-budget (which inventories the harness); this governs in-session behavior.
4 other projects use a version of this.
Adopted by
Most recently taken up by
- arjunkshah/token-skilltheir own version, first seen Oct 17, 2026
- debasish-tech/agent-skillstheir own version, first seen Oct 15, 2026
- toonight/get-shit-done-for-antigravitytheir own version, first seen Oct 8, 2026
- Lucioway/way-stacktheir own version, first seen Aug 31, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- toonight/get-shit-done-for-antigravity★ 952same name
- arjunkshah/token-skill★ 1same name
- debasish-tech/agent-skills★ 0same name
- Lucioway/way-stack★ 0same 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.
In this repository60 other files it gives its agents.
- .claude/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- analyzeSkill
- animation-disciplineSkill
- api-versioningSkill
- autopilotSkill
- browser-e2eSkill
- characterizeSkill
- clarifySkill
- codemodSkill
- constitution-compactSkill
- constitutionSkill
- context-budgetSkill
- creative-webSkill
- db-migrationSkill
- debugSkill
- detect-stackSkill
- dispatch-criteriaSkill
- dreamSkill
- experimentSkill
- fastapiSkill
- flag-cleanupSkill
- flag-rolloutSkill
- flask-realtimeSkill
- framework-detectorSkill
- front-end-designSkill
- grill-meSkill
- handoffSkill
- image-generationSkill
- implementSkill
- initiativeSkill
- instinctSkill
- loopSkill
- nextjsSkill
- observabilitySkill
- okr-alignSkill
- parallel-swarmSkill
- pivotSkill
- planSkill
- pr-bodySkill
- prime-disciplineSkill
- prod-observabilitySkill
- react-nodeSkill
- react-viteSkill
- release-trainSkill
- researchSkill
- reviewSkill
- security-guardSkill
- self-healSkill
- shipSkill
- skill-creatorSkill
- specifySkill
- tailwind-disciplineSkill
- tasksSkill
- tdd-loopSkill
- typographySkill
- verify-loopSkill
- verifySkill
- wip-checkpointSkill
- <kebab-case-skill-name>Skill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 22
If the context-monitor hook injects an [output] warning, the previous turn exceeded the growth nudge — tighten immediately.
“Common” is measured: kept by at least 6 in 10 of the 4 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
Token Budget
In-session token discipline. context-budget audits what the harness loads;
this skill governs what the session spends. (Gap-audit G8: previously
referenced from CLAUDE.md, README, ARCHITECTURE, RESEARCH §9, and
prime-discipline but never shipped.)
Output rules (the model's own tokens)
- Cite paths, don't paste files.
src/foo.ts:42, never the contents. - No preamble, no postamble. No "I'll now read…", no "Let me know if…".
- State results, don't narrate. One sentence per milestone, not per tool call.
- Don't echo back what the user (or a hook) just said.
- If the
context-monitorhook injects an[output]warning, the previous turn exceeded the growth nudge — tighten immediately.
Input rules (what enters context)
- Subagents for heavy reads (>3 files or >20K tokens) — their context dies
with them; only the conclusion returns. Use
Explore(Haiku). - Graphify MCP over grep for cross-module questions (>3 files).
- memory-recall.sh before grepping
.claude/memory/— index-backed, ≤5 lines. - Read
initiatives/active/<id>.STATE.md(≤60 lines) instead of re-deriving initiative state from specs/plans/tasks.
Cache rules
- Don't rewrite prefix surfaces mid-session: CLAUDE.md, agents/*, skill frontmatter, settings. They invalidate the prompt cache for every later turn.
- TTL is ~5 minutes and not configurable from Claude Code: turns spaced
5min apart re-pay the cache write. Keep unattended loops tight.
- Measure, don't guess:
bash .claude/scripts/cost-report.sh day→cache_hit_ratein cost-summary.json; statusline showscache:N%; harness-doctor warns underCACHE_HIT_MIN(default 40%).
Compact rules
- Same task continuing →
/compact "<focus hint>"at a clean boundary. - New task →
/clear. - The
context-monitorhook nudges at 60% and 80% estimated fill; at 80%, persist in-flight state (WIP commit, tasks/notes) before compaction.
References
- docs/RESEARCH.md §9 (sources: Anthropic context-engineering + long-running-agents posts)
- .claude/skills/context-budget/SKILL.md (harness-load inventory)
- .claude/skills/prime-discipline/SKILL.md (session-start digest of these rules)
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.

