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-listnpx skills add loncadev/baron --skill task-listgit 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 | $0.00064 | $0.00731 |
| Opus 5 | $0.00032 | $0.00365 |
| Sonnet 5 | $0.00013 | $0.00146 |
| Haiku 4.5 | $0.00006 | $0.00073 |
Grade A, and why
task-list 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
List work items
A thin, read-only wrapper over baron_issue_read op=query that maps everyday words to its normalized filters
(role, typeRole, assignee, limit). It never mutates anything.
Token → filter mapping
- Assignee:
@me/ "mine" / "bana atanan" →assignee: "@me". A bare handle (email/login) → that handle. - Role:
in_progress/ "active" / "devam eden" →role: "in_progress";in_review/ "test" / "review" →role: "in_review";backlog/ "new" →role: "backlog";ready→role: "ready";done/ "closed" →role: "done". "blocked" is not a role and not a query filter — every returned item carries ablockedboolean, so answer "what is blocked?" by filtering the results, never by sendingblockedas a role — the core rejects it. - Type:
bugs→typeRole: "bug";tasks→task;stories→story;epics→epic. - Sprint:
sprint/ "this sprint" / "aktif sprint" →iteration: "@current"(the active sprint); a literal iteration path → that iteration. On providers without sprints this yields nothing.
Filters are AND-combined. baron_issue_read op=query returns a lightweight projection (no body); default cap
is 50 — pass a higher limit only when the user asks for more.
Steps
- Parse the tokens from the argument (combinable:
@me bugs,in_review, …). - Query. One
baron_issue_read op=querycall with the mapped filters.baron_issue_read op=querytakes a singlerole, so if the user asks for a set that spans roles (e.g. "my open work" = in_progress + in_review), run one query per role and merge. Default with no argument:assignee: "@me"across the active roles (in_progress + in_review). - Present a compact table:
key · title · role · typeRole · assignee(+ the item'sbranchNamewhen present — it's the branch you'd resume with/baron:task-start). If empty, say so plainly.
Rules
- Read-only: never transition, comment, or create from this skill — that's
/baron:task-move//baron:task-new. - Don't dump raw JSON; format the rows. For a large result, show the count and the first page, and
offer to narrow the filter rather than raising
limitblindly.
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 · 47 lines · 64 tokens per session scan A 0e955d9fe5a1
task-list is a skill published in the GitHub repository loncadev/baron (1 stars, last pushed 12d ago), licensed Apache-2.0. It adds 64 tokens to every session and 731 once invoked, about $0.0003 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
csharp-bootstrap
Harness fixture bootstrap producer for the csharp project language. Minimal shape — exercises BootstrapDispatch + BootstrapRound, not real bootstrap output.
generic-bootstrap
Harness fixture bootstrap producer for the generic project language. Minimal shape — exercises BootstrapDispatch + BootstrapRound, not real bootstrap output.
coding-agent-master
Harness fixture master skill for coding pipelines. Intentionally minimal — handler-chain shape only, not real master behaviour.
node-bootstrap
Harness fixture bootstrap producer for the node project language. Minimal shape — exercises BootstrapDispatch + BootstrapRound, not real bootstrap output.
python-bootstrap
Harness fixture bootstrap producer for the python project language. Minimal shape — exercises BootstrapDispatch + BootstrapRound, not real bootstrap output.
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.