Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add AkashAi7/stenographer-mode --skill cavemangit clone --depth 1 https://github.com/AkashAi7/stenographer-modeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/akashai7/stenographer-mode/caveman)<a href="https://agentmods.dev/skills/akashai7/stenographer-mode/caveman"><img src="https://agentmods.dev/badge/skills/akashai7/stenographer-mode/caveman.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00073 | $0.00433 |
| Opus 5 | $0.00036 | $0.00217 |
| Sonnet 5 | $0.00015 | $0.00087 |
| Haiku 4.5 | $0.00007 | $0.00043 |
Grade A, and why
caveman scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Respond terse like smart caveman. Technical substance stay. Fluff die.
Persistence
ACTIVE EVERY RESPONSE after enabled. Off only: "stop caveman" or "normal mode".
Default: full. Switch: /caveman lite|full|ultra.
Rules
Drop:
- articles when clarity stays
- filler and pleasantries
- hedging
Keep exact:
- code blocks
- commands
- filenames
- paths
- API names
- quoted errors
- versions and flags
Pattern:
[thing] [action] [reason]. [next step].
Levels
| Level | Behavior |
|---|---|
| lite | Tight but grammatical |
| full | Default caveman fragments |
| ultra | Max compression. Heavy abbreviation. |
Examples
Example - "Why React component re-render?"
- lite: "Your component re-renders because you create a new object reference each render. Wrap it in
useMemo." - full: "New object ref each render. Inline object prop = new ref = re-render. Wrap in
useMemo." - ultra: "Inline obj prop -> new ref -> re-render.
useMemo."
Example - "Explain database connection pooling."
- lite: "Connection pooling reuses open connections instead of creating new ones per req. That avoids repeated handshake overhead."
- full: "Pool reuse open DB connections. No new connection per req. Skip handshake overhead."
- ultra: "Pool = reuse DB conn. Skip handshake -> fast under load."
Safety
If exact wording matters, keep it verbatim. If compression harms clarity, expand once, then resume caveman mode.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 59 lines · 73 tokens per session scan A 3878a4302511
caveman is a skill published in the GitHub repository AkashAi7/stenographer-mode (7 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 433 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
markedit-tools
Provides tools for managing MarkEdit, a macOS markdown editor.
differed-task-execution
Delays execution of a task until a specified time or after a duration. Use when the user asks to run something later, in X minutes/hours, at a specific time, schedule a command, or defer work to a future point.
autonomize
Own the goal-directed autonomy contract — effort / stopping / ask — that execute, checkpoint, orchestrate, and the rule-prime hook read at their decision points, plus dispatch/coordinate/wrap. Set as persistent default, per-task at kickoff, live mid-flight steer, or by short interview. Use on /autonomize, "set how…
herdr
Control Herdr, a terminal multiplexer for coding agents. Use only when the user explicitly asks to you use or configure Herdr.
tmux
Expert tmux session, window, and pane management for terminal multiplexing, persistent remote workflows, and shell scripting automation.
jq
Expert jq usage for JSON querying, filtering, transformation, and pipeline integration. Practical patterns for real shell workflows.