
Caveman
- 2.6k installs
- 1.1k repo stars
- Updated June 18, 2026
- juliusbrussee/cavekit
This is a copy of caveman by juliusbrussee - installs and ranking accrue to the original listing.
caveman is an agent skill that compresses SPEC.md files and spec-adjacent prose into a dense, token-efficient format preserving precision for agent consumption.
About
caveman is a spec-encoding skill from cavekit loaded by /spec, /build, and /check commands. It cuts tokens roughly 75% versus prose while staying precise, applying a grammar that drops articles, filler words, aux verbs, pleasantries, and hedging while allowing sentence fragments. caveman applies to SPEC.md writes, spec-referencing prose, and backprop entries but not code, error strings, commit messages, or PR descriptions. Developers reach for caveman when writing SPEC.md or when users say caveman, compress this, or be brief. The skill keeps agent context windows efficient without losing spec precision during automated build and check workflows.
- Reduces token usage by ~75% compared to standard prose while remaining precise
- Applies automatically on any write to SPEC.md or when user says "caveman", "compress this", or "be brief"
- Follows strict grammar rules: drop articles, fillers, aux verbs, pleasantries and hedging
- Uses 14 mathematical and logical symbols as preferred shorthand (→ ∴ ∀ ∃ ! ? ⊥ ≠ ∈ ∉ ≤ ≥ & | §)
- Preserves verbatim all code blocks, paths, URLs, identifiers, numbers, error strings, SQL, regex, JSON and YAML
Caveman by the numbers
- 2,576 all-time installs (skills.sh)
- +78 installs in the week ending Aug 4, 2026 (Skillselion tracking)
- Security screen: LOW risk (skills.sh audit)
- Data as of Aug 4, 2026 (Skillselion catalog sync)
npx skills add https://github.com/juliusbrussee/cavekit --skill cavemanAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 2.6k |
|---|---|
| repo stars | ★ 1.1k |
| Security audit | 3 / 3 scanners passed |
| Last updated | June 18, 2026 |
| Repository | juliusbrussee/cavekit ↗ |
How do you compress SPEC.md for agent token limits?
Compress SPEC.md files and any spec-adjacent prose into a dense, token-efficient format that preserves precision for agent consumption.
Who is it for?
Developers writing SPEC.md files consumed by /spec, /build, and /check agent workflows.
Skip if: Human-readable PR descriptions, commit messages, error strings, or production application code formatting.
When should I use this skill?
User writes to SPEC.md, says caveman, compress this, be brief, or triggers /spec and /build spec encoding.
What you get
Dense caveman-encoded SPEC.md and spec prose with roughly 75% fewer tokens.
- Caveman-encoded SPEC.md
- Compressed spec prose
By the numbers
- Cuts tokens ~75% versus prose while staying precise
Files
caveman — spec encoding
Applies to SPEC.md writes, spec-referencing prose, backprop entries. Does NOT apply to code, error strings, commit messages, PR descriptions.
GRAMMAR
- Drop articles (a, an, the).
- Drop filler (just, really, basically, simply, actually).
- Drop aux verbs where fragment works (is, are, was, were, being).
- Drop pleasantries.
- No hedging (skip "might", "perhaps", "could be worth").
- Fragments fine.
- Short synonyms: fix > implement, big > extensive, run > execute.
SYMBOLS
Prefer over words:
→ leads to / becomes / on <x>
∴ therefore / fix
∀ for all / every
∃ exists / some
! must / required
? may / optional / unknown
⊥ never / forbidden / nil
≠ not equal
∈ in
∉ not in
≤ at most
≥ at least
& and
| or
§ section referencePRESERVE VERBATIM
Never compress:
- Code blocks, snippets, one-liners with backticks.
- Paths:
src/auth/mw.go. - URLs.
- Identifiers: function names, variable names, env vars.
- Numbers and versions.
- Error message strings.
- SQL, regex, JSON, YAML.
- Quoted strings.
SHAPES
Invariant:
V<n>: <subject> <relation> <condition>
V1: ∀ req → auth check before handler
V2: token expiry ≤ current_time → rejectBug row (pipe table under §B):
id|date|cause|fix
B1|2026-04-20|token `<` not `≤`|V2Task row (pipe table under §T):
id|status|task|cites
T3|x|add auth mw|V1,I.apiStatus: x done, ~ wip, . todo. Escape literal | as \|.
Interface:
<kind>: <name> → <shape>
api: POST /x → 200 {id:string}
cmd: `foo bar <arg>` → stdout JSON
env: FOO_KEY ! setEXAMPLES
Bad:
The system should ensure that every incoming request is properly authenticated before being forwarded to its corresponding handler function.
Good:
V1: ∀ req → auth check before handler
Bad:
We discovered that the token expiration check in the middleware was using a strict less-than comparison operator, which meant tokens were being rejected at the exact moment of their expiry.
Good:
B1: token<not≤→ reject @ expiry boundary.
Bad:
The POST endpoint at /x accepts a JSON body and returns a 200 response with an object containing the created id.
Good:
api: POST /x → 200 {id}
BOUNDARIES
- User asks for prose explanation → switch to normal English.
- Spec documents for external review (RFC, pitch) → normal English.
- Commit message → normal English (git readers expect it).
- Diff comment in code → normal English.
WHEN UNSURE
If cutting a word loses a fact, keep it. Caveman is compression, not amputation.
Related skills
FAQ
How much does caveman reduce SPEC.md token usage?
caveman cuts tokens roughly 75% compared to prose SPEC.md writes while preserving precision, using fragment-based grammar that removes articles, filler, and hedging.
What files does caveman apply to?
caveman applies to SPEC.md writes, spec-referencing prose, and backprop entries. It does not apply to code, error strings, commit messages, or PR descriptions.
Is Caveman safe to install?
skills.sh reports 3 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.