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 marinahaugen/polymorph-mindset-plugins --skill autonomous-flowgit clone --depth 1 https://github.com/marinahaugen/polymorph-mindset-pluginsWrote 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/marinahaugen/polymorph-mindset-plugins/autonomous-flow)<a href="https://agentmods.dev/skills/marinahaugen/polymorph-mindset-plugins/autonomous-flow"><img src="https://agentmods.dev/badge/skills/marinahaugen/polymorph-mindset-plugins/autonomous-flow/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/marinahaugen/polymorph-mindset-plugins/autonomous-flow"><img src="https://agentmods.dev/badge/skills/marinahaugen/polymorph-mindset-plugins/autonomous-flow.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 | $0.00239 | $0.02628 |
| Opus 5.5 | $0.00096 | $0.01051 |
| Sonnet 5.5 | $0.00048 | $0.00526 |
| Haiku 4.5 | $0.00024 | $0.00263 |
Grade A, and why
autonomous-flow 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 — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autonomous Flow
Take just-implemented work through every gate between "code written" and "PR ready for human review," without stopping to ask permission between stages. The human's review window is the finished PR — your job is to make that PR as correct, clean, and well-narrated as possible before they look.
When to use
Invoke this after the implementation tasks of a plan are done (or nearly done) and you want to ship. Signals: "run the autonomous flow", "finish this", "take it to PR", "ship it", or you've just completed the last task of an implementation plan. If implementation is clearly not finished, say so and finish it first — this skill is the finish line, not the whole race.
Operating principles
- Run continuously. Do not pause between stages to ask "should I continue?" The user opted into an autonomous flow. The only reasons to stop are a hard blocker you cannot resolve, a genuine ambiguity that changes the outcome, or completion. Surface those; otherwise keep going.
- Evidence over assertion. Never claim a stage passed without showing the command output that proves it. A stage with failing checks is not done.
- Fix as you go. Each stage that can surface issues has a fix-loop: fix, re-run that stage's check, repeat until green — then advance.
- Prefer project skills, degrade gracefully. Where a project ships its own skill for a stage, use it. Otherwise use the generic fallback named in that stage. Announce which one you picked.
- Respect repo conventions. Branch strategy, commit message format, and signing rules come from the
repo (check its
CLAUDE.md/ contributing docs). Never assumemainis the base branch.
Step 0 — Set up the progress tracker (do this first)
Before any stage runs, create a todo list (TodoWrite, or the session's task tool) with one item per
stage below, all pending. This is how the user monitors the run. At each stage boundary, mark the
finished item completed, the next one in_progress, and post a one-line progress bar so progress is
visible even without opening the todo panel:
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.
- 1mo ago First seen · 209 lines · 239 tokens per session scan A 532f8b573f42
autonomous-flow is a skill published in the GitHub repository marinahaugen/polymorph-mindset-plugins (4 stars, last pushed 4mo ago), licensed MIT. It adds 239 tokens to every session and 2,628 once invoked, about $0.0010 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 2026-08-31.
Other skills, from other repositories
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
pr
Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout.
merge-batch
Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.
otto-pr-review-loop
Run Polly and OCR on a PR until all findings settle.
engram-branch-pr
PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.
verify-behavior
Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…