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/fprochazka/claude-code-plugins/team-workflow-identifynpx skills add fprochazka/claude-code-plugins --skill team-workflow-identifygit clone --depth 1 https://github.com/fprochazka/claude-code-pluginsWhat 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 | $0.00092 | $0.01412 |
| Opus 5 | $0.00046 | $0.00706 |
| Sonnet 5 | $0.00018 | $0.00282 |
| Haiku 4.5 | $0.00009 | $0.00141 |
Grade A, and why
team-workflow-identify 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
team-workflow-identify
Ground the agent in the project's issue tracker, team and workflow states before any command reads or moves a ticket. Every value is discovered at run time. This skill hardcodes no team name, no team id and no status name — a skill that carries them turns stale the day someone renames a state.
The output is the block in "Output contract" below. Print it, and the calling command carries it for the rest of the run.
Source order
The order is fixed. Do not skip ahead.
-
Context already loaded.
CLAUDE.md,AGENTS.md, everything they pull in through@includes, and any memory already in context. These are free to read and they are the place a team writes its own conventions down. Search the context you already hold first — aCLAUDE.mdthat is a single@README.mdline answers nothing on disk while its included content sits in your context. Grep the files on disk as a supplement, and follow every@include you find:grep -rniE 'linear|jira|gitlab issue|github issue|team (key|id)|status|workflow|ticket|branch nam|^@' CLAUDE.md AGENTS.md 2>/dev/null | head -30 -
The repo
README.md. Many repos repeat the tracker facts there. -
The tracker API — last resort, and never silent. See "Stop before the API".
Stop before the API
If sources 1 and 2 do not answer, stop and tell the user what is missing. Do not go fishing through the API on your own. An API answer that lands nowhere is discovered again on every future run.
Offer two ways to persist the answer, and name the concrete file for each:
- An edit to one of the loaded convention files — say which one, for example
./AGENTS.mdor./CLAUDE.md. - A Claude memory.
The user picks. Then query the tracker API, write the result into the chosen place, and continue. The next run reads it from source 1.
What to extract
- Tracker — Linear, Jira, GitLab issues, GitHub issues, or none.
- Team — display name, key, and id where the tracker has one. These are three different strings for one team. Never derive one from another.
- Ticket ID pattern —
TEAM-123,#123, or a tracker URL. The commands parse branch names and MR titles with it. - Branch convention — the documented pattern if there is one, for example
<initials>/<TICKET>-<slug>. Reportnonewhen nothing documents it, and do not invent one from the branches that happen to exist. - Workflow states — see below.
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 · 86 lines · 92 tokens per session scan A 3b12a61eba87
team-workflow-identify is a skill published in the GitHub repository fprochazka/claude-code-plugins (11 stars, last pushed 4d ago), licensed MIT. It adds 92 tokens to every session and 1,412 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 2026-08-30.
Other skills, from other repositories
paperclip
Interact with the Paperclip control plane API for task coordination and governance. Use when checking assignments, updating issue status, posting comments, delegating work, managing routines, or calling Paperclip API endpoints.
wayfinder
Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
setup-matt-pocock-skills
Configure this repo for the engineering skills: set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.
github-labels-query
List GitHub repository labels with perpage pagination and name filtering support.
retro
Facilitate a structured sprint retrospective — what went well, what didn't, and prioritized action items with owners and deadlines. Use when running a retrospective, reflecting on a sprint, creating action items from team feedback, or learning how to run effective retros.
gsd-audit-milestone
Audit milestone completion against original intent before archiving.