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 oliverjueguen/workingon-claude-skill --skill skillgit clone --depth 1 https://github.com/oliverjueguen/workingon-claude-skillWrote 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/oliverjueguen/workingon-claude-skill/skill)<a href="https://agentmods.dev/skills/oliverjueguen/workingon-claude-skill/skill"><img src="https://agentmods.dev/badge/skills/oliverjueguen/workingon-claude-skill/skill/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/oliverjueguen/workingon-claude-skill/skill"><img src="https://agentmods.dev/badge/skills/oliverjueguen/workingon-claude-skill/skill.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 | $0.00092 | $0.01544 |
| Opus 5 | $0.00046 | $0.00772 |
| Sonnet 5 | $0.00018 | $0.00309 |
| Haiku 4.5 | $0.00009 | $0.00154 |
Grade A, and why
workingon 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 10d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- workingon — 92% identical, 4 lines differ
How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bridge between this session and the ticketing tool. A local ledger, filled in by hooks, records what was asked, which files were touched, which commits landed and which notable commands ran.
WO = node {{WORKINGON}}. Every command accepts --json.
Rules
- Record, do not redo. The work is already done; this only documents it.
- One ticket per task, not per session. Work continuing the linked ticket becomes a comment. A different topic becomes a new ticket.
- Never invent anything that is not in the ledger or in the conversation.
- Write in the user's language.
- End the turn with one short line: ticket reference and URL. Nothing else.
The workspace may be shared
Colleagues may be looking at these boards.
- Never create projects, boards or repositories, and never touch tickets this tool did not create.
- Never delete anything.
deleteexists for the person to run, not for you. If asked to delete, show what would go and wait for explicit confirmation. - Only write to the destination that
ledgerresolves. If it saysUNDECIDED, ask first. Never pick a destination that merely looks right. - If
createorcommentanswer[SIMULATED], nothing was written. Say exactly that, without implying a ticket exists.
Default flow
1. Read the state.
WO ledger --session ${CLAUDE_SESSION_ID}
Returns the folder, branch, destination, linked ticket and the work not recorded yet. If the destination is UNDECIDED, go to Undecided folder.
2. Decide.
- Linked ticket and the work continues it: progress comment (step 3b).
- Linked ticket but this is a different topic: new ticket (step 3a).
- No linked ticket: search before creating.
If one is clearly the same thing, link it withWO find "keywords" --session ${CLAUDE_SESSION_ID}WO link --issue <id> --session ${CLAUDE_SESSION_ID} --keep-unsyncedand go to 3b. Otherwise create.
3a. Create.
WO create --session ${CLAUDE_SESSION_ID} --title "Title" --body-file - <<'END'
<markdown body>
END
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.
- 10d ago First seen · 140 lines · 92 tokens per session scan A 1c2fa6425ba3
workingon is a skill published in the GitHub repository oliverjueguen/workingon-claude-skill (6 stars, last pushed 24d ago), licensed MIT. It adds 92 tokens to every session and 1,544 once invoked, about $0.0005 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
daf-workflow
DevAIFlow session context loader — reads session metadata, issue tracker tickets, and context files. Auto-activates when DAFSESSIONNAME is set. Also useful when asked about current task, session status, or workflow steps for daf open, daf new, daf git new, daf jira new, and daf investigate.
split-and-ship
Execute an approved split plan, shipping each change group separately as its own branch and PR or as sequential commits on the current branch. Use when the user asks to "split and ship", "ship the split plan", "create separate PRs", or "split changes into branches".
do
Work an increment task by task through the ledger: task next, claim, implement, commit, task done with evidence. Use when saying "implement", "start working", or "continue increment".
cross-repo-cache
Check if cross-repo coordinator results can be reused, avoiding redundant Sonnet agent launches. Compares peer repo git hashes against stored hashes from last coordinator run. Triggers on: entering Phase 1.4.1, checking cross-repo cache, before discovering peers. Returns CROSSREPOCACHEHIT with cached status or…
creating-issues-and-pull-requests
Use when creating GitHub pull requests or issues with template compliance. Triggers: 'create a PR', 'open a pull request', 'file an issue', 'create issue'. Also invoked by finishing-a-development-branch. NOT for: deciding whether to merge or PR (use finishing-a-development-branch).
work-story
Work a user story end to end — fetch the ticket, plan (with approval), implement, verify the applicable gates, self-review, open the PR, and update the tracker. Use when given an issue key like PROJ-1234, ENG-42, or.