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 agentmods add skills/loncadev/baron/task-movenpx skills add loncadev/baron --skill task-movegit clone --depth 1 https://github.com/loncadev/baronWhat 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 | $0.00076 | $0.01265 |
| Opus 5 | $0.00038 | $0.00633 |
| Sonnet 5 | $0.00015 | $0.00253 |
| Haiku 4.5 | $0.00008 | $0.00127 |
Grade A, and why
task-move 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 2d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Move a work item to a role
Baron's baron_issue_move op=transition resolves an abstract role to the provider's native
state/column atomically (Azure: state + board column; GitHub: label + open/closed). This skill wraps
it with the reference's governance: backward and reopen moves require a reason, and the reason is
recorded on the item before the state changes.
The role order (the guard rule)
backlog(0) → ready(1) → in_progress(2) → in_review(3) → done(4)
Blocking is not on this line at all: it is an orthogonal flag set by `baron_issue_move op=block` and cleared
by `baron_issue_move op=unblock`, and it leaves the role untouched.
Classify the move from the item's current role to the target:
- advance — to a higher index → just move.
- regress — to a lower index (not from
done) → reason required. - reopen — from
doneto any active role → reason required. - noop — same role → report and stop (idempotent, nothing to do).
Block / unblock are not moves at all. They set and clear an orthogonal flag, so they never appear
in the table above and never change the role. Use baron_issue_move { op: "block", id, reason } — the reason is
required by the engine, not just by this skill, and it is posted on the item before the flag is set —
and baron_issue_move { op: "unblock", id, reason? }. A blocked item keeps the role it is blocked in, so there is
nothing to "move back to" on unblock.
Steps
- Resolve inputs. If the user asked to block or unblock, go to Blocking below — it is not a
move. Otherwise the target
rolefrom the argument (must be one of the five workflow roles — reject anything else, listing the valid ones). Theid: from the argument, else derive it from the current branch (<prefix>/<id>-<slug>); if neither, ask. - Reason. Look up what the move would be —
baron_issue_read { op: "classify", id, role }answersadvance/regress/reopen/noopwithout moving anything. For regress and reopen, ask the user for a one-line reason (open-ended, so ask directly rather than with a menu). Asking first is better UX than handing them a refusal — but it is not what makes the rule hold. - Run the recipe — call
baron_recipe_runexactly once:
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.
- 2d ago First seen · 88 lines · 76 tokens per session scan A 795d1a98757e
task-move is a skill published in the GitHub repository loncadev/baron (1 stars, last pushed 11d ago), licensed Apache-2.0. It adds 76 tokens to every session and 1,265 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
issue-triage
Issue triage: audit open issues, categorize, detect duplicates, cross-ref PRs, risk assessment, post comments. Args: "all" for deep analysis of all, issue numbers to focus (e.g. "42 57"), "en"/"fr" for language, no arg = audit only in French.
github-tool
GitHub integration tool for listing and creating issues and PRs via the gh CLI wrapper. Use when: creating or listing issues or pull requests, or checking repository work on GitHub.
a11y-remediate
Use to produce a leader-facing remediation proposal from one or more /a11y-audit outputs plus team and product context. Translates audit findings into sprint plans, staffing asks, customer-facing language, compliance rollups, and critical-path analysis. Refuses to fabricate numbers, owners, or commitments beyond the…
prioritize
Prioritize triaged/investigated issues — recommends shortlist, backlog, won't fix, or community contribution with priority signals and draft communications.
azure-devops
Manage Azure DevOps projects, work items, repos, PRs, pipelines, wikis, test plans, security alerts, variable groups, environments/approvals, branch policies, and attachments. Use when user asks to: manage sprints, create/update work items, list repos, create PRs, run pipelines, search code, manage wiki pages, check…
finn-build
Claim the next safe agent-ready issue from Linear, implement it, and open a PR. Use when asked to run Finn-loop's builder, work the approved queue, or fix Finn-loop review feedback. Designed for /loop; one pass does one unit of work.