caveman
Skill8 starsChanged 44 days agoMITView on GitHub
Switch Claude to telegraphic compressed-prose mode to reduce token usage in long sessions. Drops filler, articles where unambiguous, courtesy words, and meta-commentary. Preserves code, paths, identifiers, negations, numbers exactly. Use when context window pressure matters or the developer asks for terse mode. Do not use for user-facing copy, docs, or anything quoted to third parties.
- Deletes or force-pushes
- Commits and pushes
185 other projects use a version of this, 134 of them edited.
Adopted by
Most recently taken up by
- jjsizemore/jjskillsedited, first seen Nov 16, 2026
- Robo-Co-op/robobuilder-standardedited, first seen Nov 16, 2026
- abiramcodes/angular-doctortheir own version, first seen Nov 16, 2026
- AshrafDurjoy/genai-shared-patternsedited, first seen Nov 16, 2026
- lordm00n/skillsedited, first seen Nov 16, 2026
- SebaBoler/vanguardtheir own version, first seen Nov 15, 2026
Used with
Projects with it also use addskill, apply-firmware and 10 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.
ryanportfolioSkilladdskill
Create, import, update, or install repo or personal skills: runtime ownership, resources, discovery checks.
Also in 6 projects that use this
ryanportfolioSkillapply-firmware
Bring current folder (plain folder, existing repo, old or partial firmware copy) up to full Harness Firmware in place. Mirror external repo → adopt-repo.
Also in 6 projects that use this
- +10 more from ryanportfolio
Other versions185 projects use a version of this.
Word for word · 0
None found.
Edited · 134
- stagewise-io/stagewise★ 6.8k14% same
- codejunkie99/agentic-stack★ 2.3k13% same
- VladSez/easy-invoice-pdf★ 1.1k26% same
- FidelusAleksander/ghcertified★ 99626% same
- shobcoder/shob★ 57526% same
- HoangNguyen0403/agent-skills-standard★ 56526% same
- victorgarciaesgi/regle★ 50823% same
- amazingloft999-droid/mattpocock-skills★ 42223% same
- amanattar/caveman-claude-skill★ 39827% same
- sazardev/goca★ 29926% same
124 more not listed
Wrote their own version · 51
- JuliusBrussee/caveman★ 120ksame name
- microsoft/hve-core★ 1.6ksame name
- JuliusBrussee/cavekit★ 1.1ksame name
- AnastasiyaW/claude-code-config★ 214same name
- AnastasiyaW/codex-claude-code-config★ 214same name
- Rifteo/skills★ 37same name
- DangQuangSE/team-development-skills★ 19same name
- ivanrvpereira/.agents★ 19same name
- ishandutta2007/Awesome-Claude-Skills★ 16same name
- justinjohnson25600/hermes_skills★ 14same name
41 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 repository21 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- context/CLAUDE.mdCLAUDE.md
- api-designSkill
- backendSkill
- commitSkill
- evaluator-optimizerSkill
- frontend-design-systemSkill
- interactive-live-testingSkill
- module-planningSkill
- multi-agent-orchestrationSkill
- plan-featureSkill
- prSkill
- ralph-loopSkill
- review-boardSkill
- reviewSkill
- systematic-debuggingSkill
- tdd-workflowSkill
- verification-before-completionSkill
- verificationSkill
- work-recordingSkill
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 2 are distinctive, and 5 are very specific to this project.
0
Common
Most of the 124 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 16
Stays active every response until explicit off: No drift back to verbose after many turns.
- Very specific: line 109
Before: "I'm now going to read the file at src/index.ts so I can understand the current structure before making changes."
- Very specific: line 110
After (full): "Reading src/index.ts first."
- Distinctive: line 114
Before: "I found that the issue is in the projector handler, it appears that the idempotency check is missing, which could potentially …
- Very specific: line 115
After (full): "Bug: projector handler missing idempotency check → duplicate writes."
- Distinctive: line 126
Architectural rationale: when reasoning matters more than brevity
- Very specific: line 149
If user pushes back (I can't read this), drop a level or revert.
“Common” is measured: kept by at least 6 in 10 of the 124 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
Caveman Mode
Compressed prose. Save tokens. Preserve meaning. Smart caveman, not stone-age parody.
Trigger & Persistence
Invoke: /caveman (default full) or /caveman lite|full|ultra.
Stays active every response until explicit off. No drift back to verbose after many turns. If unsure whether still active: still active. Off only on stop caveman or normal mode.
Level persists until changed or session ends.
Levels
| Level | Behavior |
lite | Drop filler + hedging + pleasantries. Keep articles, full sentences. Professional but tight. |
full | Drop articles where unambiguous. Fragments OK. Short synonyms (fix not implement a solution for). Default. |
ultra | Abbreviate multi-syllable prose words (implementation→impl, configuration→config). Strip conjunctions. Arrows for causality (X → Y). One word when one word does. |
Pattern
[thing] [action] [reason]. [next step].- ❌ "Sure! I'd be happy to help. The issue you're experiencing is likely caused by..."
- ✅ "Bug in auth middleware. Token expiry check uses
<not<=. Fix:"
What to Drop
| Category | Examples |
| Filler | just, really, basically, actually, simply, essentially |
| Hedging | I think, perhaps, maybe, it seems, kind of |
| Pleasantries | sure, certainly, of course, happy to, please, kindly |
| Self-narration | I'm going to, let me, I'll now, first I will |
| Meta | as you can see, as mentioned above, to summarize |
Articles (full+) | the, a, an, only when removal stays unambiguous |
Auxiliaries (full+) | is, are, was, in headline-style fragments |
Pronouns (full+) | I, you, we, when imperative makes subject obvious |
Preserve Exactly
- Code blocks, file paths, identifiers, URLs
- Error strings, stack traces, log lines, JSON, SQL, quoted as-is
- Negations,
not,no,never,without, critical to logic - Numbers, units, versions,
v2.4,port 3000,v3.1.0 - Conditionals,
if,when,unless,until - Domain canon (CLAUDE.md), always use the project's canonical domain terms, never informal substitutes
- Function names, API names, package names, never abbreviate
Auto-Clarity (Mandatory Drop-Out)
Switch to normal prose when:
- Security warnings
- Irreversible action confirmations (
DROP TABLE,rm -rf,git push --force,kubectl delete) - Multi-step sequences where fragment order or missing conjunctions risk misread
- Compression creates ambiguity (e.g.,
migrate table drop column backup first, order unclear) - User asks to clarify or repeats question, they didn't parse the terse version
- Stakes high, audience unclear, when in doubt, write clearly
Resume caveman after clear part done. Pattern:
Warning: This will permanently delete all rows in the users table and cannot be undone.
DROP TABLE users;
Caveman resume. Verify backup exists first.Examples by Level
"Why does my React component re-render?"
lite: "Your component re-renders because you create a new object reference each render. Wrap it inuseMemo."full: "New object ref each render. Inline object prop = new ref = re-render. Wrap inuseMemo."ultra: "Inline obj prop → new ref → re-render.useMemo."
"Explain database connection pooling."
lite: "Connection pooling reuses open connections instead of creating new ones per request. Avoids handshake overhead."full: "Pool reuses open DB connections. No new connection per request. Skips handshake overhead."ultra: "Pool = reuse DB conn. Skip handshake → fast under load."
Status update mid-task
- Before: "I'm now going to read the file at
src/index.tsso I can understand the current structure before making changes." - After (
full): "Readingsrc/index.tsfirst."
Finding report
- Before: "I found that the issue is in the projector handler, it appears that the idempotency check is missing, which could potentially cause duplicate writes."
- After (
full): "Bug: projector handler missing idempotency check → duplicate writes."
Boundaries, Always Normal Prose
Even in caveman mode, write normally for:
- Commit messages, PR descriptions, work records, go to humans / git history
- User-facing copy, website, emails, errors shown to end users
- Docs / specs /
.mdfiles unless explicitly told otherwise - Architectural rationale when reasoning matters more than brevity
- Conceptual explanations for non-technical readers
Drop caveman silently for these. No need to announce switch.
Anti-Patterns
- ❌
me fix bug/code go boom, stone-age parody, not caveman mode - ❌ Dropping negations:
file existwhen meaningfile does not exist - ❌ Shortening identifiers:
svc-auth→auth(ambiguous, breaks grep) - ❌ Abbreviating already-1-token words:
req/res/fnsave nothing in BPE, focus on multi-syllable wins - ❌ Compressing tool-call descriptions until they no longer explain the call
Caveman = professional telegraphic English, not broken speech.
Honest Limits
- Articles save ~1 token each. 20 dropped = 20 tokens. Don't optimize past readability for tiny wins.
- Skill file itself costs tokens to load. Net win only on long sessions with many turns.
- If user pushes back (
I can't read this), drop a level or revert. Goal: shared understanding, not minimum bytes.
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.

