Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/oleg494/coding-kitnpx agentmods add skills/oleg494/coding-kit/autonomous-workWrote 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/oleg494/coding-kit/autonomous-work)<a href="https://agentmods.dev/skills/oleg494/coding-kit/autonomous-work"><img src="https://agentmods.dev/badge/skills/oleg494/coding-kit/autonomous-work/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/oleg494/coding-kit/autonomous-work"><img src="https://agentmods.dev/badge/skills/oleg494/coding-kit/autonomous-work.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 | $0.00118 | $0.02379 |
| Opus 5 | $0.00059 | $0.01189 |
| Sonnet 5 | $0.00024 | $0.00476 |
| Haiku 4.5 | $0.00012 | $0.00238 |
Grade A, and why
autonomous-work 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 today.
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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autonomous Work
Broad authorization to choose and continue useful work — executed without manufacturing a task for the user and without pretending completion.
Activation & scope
- Activates on broad authorization: "do useful work", "pick what matters", "keep going without asking", "работай сам", "делай что полезно". The user has authorized selection and continuation, not a specific task list.
- Bounded requests are unchanged: "fix this bug", "review this PR", "add this flag" keep their existing scope. Autonomous work adds no scope to a request that already names its scope.
- Opt-in, not a mode override: this skill is not always-on, and it does not
replace
STRICT_AUDITorEXPLORATORY_PROTOTYPE. Under a read-only or strict-audit instruction, autonomy selects only read-only/audit work; it never upgrades permissions, and it never treats autonomy as a reason to weaken a constraint the user or host set. - If no useful in-scope work remains, say so plainly and stop. Idle is an honest outcome; invented work is not.
Core loop
SELECT ──→ DO ──→ VERIFY ──→ RECORD ──→ NEXT
│ │ │ │ │
▼ ▼ ▼ ▼ ▼
evidence smallest observed durable continue
-backed change result evidence without ceremony
objective
- Select the highest-value objective that is in scope and backed by evidence (failing test, reported symptom, explicit TODO, uncovered contract, known defect). Say in one line why it is the next thing.
- Do the smallest correct change that closes it — normal method skills still apply (plan → TDD → implement → verify → report).
- Verify by observation: run the specific check, scenario, or command that covers the change. Unverified work is not a completed objective.
- Record the evidence and the resulting state durably (file, test, log, changelog, handoff) so a later session can resume without re-deriving it.
- Next: pick the next objective and continue. Do not ask permission for each step once broad authorization is given.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today First seen · 190 lines · 118 tokens per session scan A 8522311cbbdc
autonomous-work is a skill published in the GitHub repository oleg494/coding-kit (2 stars, last pushed today), licensed MIT. It adds 118 tokens to every session and 2,379 once invoked, about $0.0006 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 2026-09-09.
Other skills, from other repositories
tip
Deliver a transformative life perspective shift and a productivity tip. Use when the user invokes /tip or wants non-technical inspiration or a fresh mental model.
adhd-output-style
This skill should be used when the user asks for "ADHD output", "fewer output tokens", "short numbered steps", "limited working memory formatting", or explicitly invokes "adhd-output-style".
schedule-meeting
Schedule meetings, calls, or events on the calendar. Use when the user wants to book, plan, schedule, or set up a meeting or appointment with someone at a time.
weekly-brief
Brief me on my week, my day, or what to focus on. Use for "brief me", "what's on my week", "what should I focus on", "my day", "catch me up", morning briefing.
atomicmail
Read and write email through the Atomic Mail from an AI agent. Handles proof-of-work authentication and JMAP so the agent thinks in JMAP method calls. Use when the user asks to register an email inbox, list mailboxes, fetch or send email.
session-librarian
Organize sessions by prompt: find, rename, archive, prune.