Borrowing it
Nothing to install: this file belongs to ccevans/bobbycode. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ccevans/bobbycode/main/.claude/skills/bobby-freewill/SKILL.mdgit clone --depth 1 https://github.com/ccevans/bobbycodeWrote 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/ccevans/bobbycode/bobby-freewill)<a href="https://agentmods.dev/skills/ccevans/bobbycode/bobby-freewill"><img src="https://agentmods.dev/badge/skills/ccevans/bobbycode/bobby-freewill/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/ccevans/bobbycode/bobby-freewill"><img src="https://agentmods.dev/badge/skills/ccevans/bobbycode/bobby-freewill.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 | $0.01294 |
| Opus 5 | $0.00046 | $0.00647 |
| Sonnet 5 | $0.00019 | $0.00259 |
| Haiku 4.5 | $0.00009 | $0.00129 |
Grade C, and why
bobby-freewill scanned grade C with 1 finding 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 5d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
subject to your judgment: no `rm -rf`, `DROP TABLE`, `git push --force`, `git reset --hard`, How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bobby Freewill Skill
One agent takes the ticket from wherever it is to shipping. You get the goal, the constraints you could not have inferred, and nothing else. Every other decision is yours.
Why this file is short
Bobby's other build skills are long on purpose — they were written for models that drift without a script. Opus 5 and Fable 5 do not need the script, and on them a long one costs you something real: attention spent on compliance, and an agent that finishes the checklist instead of the ticket. Prescribed procedure also caps the work at whatever the procedure's author imagined; your own read of this codebase is usually better.
So this file states only what you cannot work out by reading the repo — Bobby's conventions, the invariants, and where you must stop. How to approach the problem, whether the test comes first, how far to refactor, what evidence is convincing: your call, and you own the outcome.
Do not add steps to this file. If freewill keeps getting something wrong, that is a
learning (bobby learn bobby-freewill "pattern" "description"), or a sign that kind of
ticket belongs in the default workflow. It is not a reason to grow a procedure here.
When not to use freewill
Freewill collapses plan → build → review → test into one agent, so it gives up the thing those stages exist for: a second pair of eyes that did not write the code. Say so and route elsewhere when the ticket is:
- Security-sensitive — auth, payments, crypto, secrets, permissions, user data. Use
--workflow secure; a self-review is not an audit. - Underspecified — you cannot state the acceptance criteria in your own words after
reading
ticket.md. Use the default workflow, orbobby run vet {ID}first. - An epic, or big enough that you would want the plan reviewed before code exists.
Freewill's home ground is a ticket whose intent is clear and whose blast radius you can see.
What you cannot infer from the codebase
- The ticket is the contract.
.bobby/tickets/{ID}*/ticket.md— its Description and Acceptance Criteria are the deliverable. Do not quietly widen or narrow them. If you think the ticket is wrong, say so in one or two sentences, then build it as written and flag it. - Stage is tracked by the CLI, not by editing files.
bobby ticket move {ID} shipwhen done,bobby ticket move {ID} block "reason"when you cannot finish. Hand-editing frontmatter does not register. - Never commit to main/master.
git branch --show-currentfirst; if you are on it,git checkout -b tkt-{ID}before writing anything. - Finish clean. Commit every file you changed.
git status --shortmust be clean when you are done — an uncommitted change is invisible to every stage after you. - Evidence, not assertion. Paste the test and lint output. "Tests pass" without the output is not a claim anyone downstream can act on.
- Durable lessons go in learnings, not in your final message:
bobby learn bobby-freewill "pattern" "description".
What ships with it
2 files 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.
- 5d ago First seen · 97 lines · 93 tokens per session scan C fb1d007c2553
bobby-freewill is a skill published in the GitHub repository ccevans/bobbycode (6 stars, last pushed 3d ago), licensed MIT. It adds 93 tokens to every session and 1,294 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
amq-spec
Use two agents to research a design independently and converge on one specification through AMQ. Trigger for collaborative design or messages labeled workflow:spec; use amq-cli for ordinary coordination.
productivity
Personal productivity, time management, project management, team productivity, automation, and process improvement skills. GTD, time-blocking, focus systems, async workflows. Triggers on: productivity, time management, GTD, focus, deep work, async, project management, workflow, habits.
python-release
Handle Python SDK release, build, bump, packaging metadata, PyPI client pin, uv.lock, nox/build workflow, and publish verification changes. Use for Python release process work or dependency pin bumps; do not use for ordinary Python feature implementation.
apple-reminders
Manage Apple Reminders via the remindctl CLI on macOS — list, add, complete, delete, manage lists.
feishu-openapi-skill
Operate Feishu or Lark IM APIs through UXC with a curated OpenAPI schema, tenant-token bearer auth, and chat/message guardrails.
agent-desktop
Use the built-in Computer sub-agent with agent-desktop for macOS desktop automation. Apply when a task needs application launching, accessibility snapshots, stable element refs, window focusing, semantic clicks/typing, or visual confirmation outside the browser sandbox.