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 AcKeskin/contexture --skill autonomizegit clone --depth 1 https://github.com/AcKeskin/contextureWrote 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/ackeskin/contexture/autonomize)<a href="https://agentmods.dev/skills/ackeskin/contexture/autonomize"><img src="https://agentmods.dev/badge/skills/ackeskin/contexture/autonomize/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ackeskin/contexture/autonomize"><img src="https://agentmods.dev/badge/skills/ackeskin/contexture/autonomize.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00093 | $0.03228 |
| Opus 5.5 | $0.00037 | $0.01291 |
| Sonnet 5.5 | $0.00019 | $0.00646 |
| Haiku 4.5 | $0.00009 | $0.00323 |
Grade A, and why
autonomize 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
autonomize
The goal-directed autonomy organ. It owns one contract — how hard to push, when to stop, when to ask — and is the single writer of it. The existing workflow organs are readers of that contract at their decision points: one owner, many readers (the retrospect-core shape). The contract is leverage (set calibration once, the whole workflow shares it), not ceremony.
The two problems it solves:
- Grounding-before-asking — the model re-asks mid-task what the front-loaded spec/example/checklist already answers. The contract's
askposture rides the rule-prime hook as a recall-before-ask reminder: scan the handed-over artefact and state why the answer is not derivable before interrupting. - Effort / stopping calibration — the model under- or over-builds, forcing "keep going" / "leave it here, perfect next session". The contract's
effort+stoppingfields are the dial the organs read to calibrate.
/autonomize → .claude/autonomy/active.md → read by execute / checkpoint / orchestrate / dispatch / coordinate / wrap / the rule-prime hook
The contract object
One object, three fields, persisted at .claude/autonomy/active.md (gitignored, session-scoped):
# .claude/autonomy/active.md
effort: balanced # minimal | balanced | thorough | exhaustive
# depth-of-iteration AND the loop's willingness-to-continue
stopping: criteria-met # criteria-met | diminishing-returns | budget | user-anytime
# the STOPPING POSTURE — criteria-met DEFERS to the spec's
# done_criteria; it does not redefine "done"
ask: forks-only # forks-only | every-step | until-blocked
# a POINTER, not a new protocol:
# forks-only → act-dont-ask (reversible) + ambiguity-depth
# every-step → confirm each consequential step
# until-blocked → run until genuinely blocked or irreversible
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.
- 1mo ago First seen · 165 lines · 93 tokens per session scan A 2ee8c4ca0576
autonomize is a skill published in the GitHub repository AcKeskin/contexture (2 stars, last pushed 2mo ago), licensed MIT. It adds 93 tokens to every session and 3,228 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
low-code-platforms
Low-code and internal tool platforms including Retool, Supabase, Appsmith, Tooljet, n8n, and Zapier. Use when building admin panels, internal tools, workflow automations, or integrating low-code platforms with custom code.
agent-cli-developer
Specialist subagent: Command-line tool development, argument parsing, interactive prompts, and terminal UI specialist. Use when building CLI tools, implementing interactive terminal interfaces, or designing command-line experiences. Trigger phrases: CLI, command-line, argument parsing, interactive prompt, shell…
steno
Shorthand-first communication mode for token reduction w/ better readability than caveman mode. Compresses resps through consistent abbreviations, symbolic links, and dropped filler while keeping technical precision and exact literals. Use when user says "steno mode", "shorthand mode", "compressed resps", "token…
caveman
Ultra-compressed communication mode. Cuts token usage by dropping filler, articles, and soft phrasing while keeping technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Supports levels: lite, full, ultra.
morning
Render the user's morning brief as a styled HTML artifact, or set it up as a recurring weekday task. Use only when the user explicitly asks to run, see, or set up their morning brief, or if they invoke /morning by name. A question about their day, schedule, or calendar is not by itself a request for the brief; answer…
computer-use
Read this skill before the first step of any request to do something in an app on the person's own computer (Notes, Finder, System Settings, any desktop app), to look at their screen, or for "computer use". Computer use (desktop control) lets Claude take screenshots of the person's desktop and control it with clicks…