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.
git clone --depth 1 https://github.com/TeamManagementPlugin/claude-pluginWrote 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/commands/teammanagementplugin/claude-plugin/custom-protocol-create)<a href="https://agentmods.dev/commands/teammanagementplugin/claude-plugin/custom-protocol-create"><img src="https://agentmods.dev/badge/commands/teammanagementplugin/claude-plugin/custom-protocol-create/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/commands/teammanagementplugin/claude-plugin/custom-protocol-create"><img src="https://agentmods.dev/badge/commands/teammanagementplugin/claude-plugin/custom-protocol-create.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 | $0.00012 | $0.00520 |
| Opus 5.5 | $0.00005 | $0.00208 |
| Sonnet 5.5 | $0.00002 | $0.00104 |
| Haiku 4.5 | $0.00001 | $0.00052 |
Grade A, and why
custom-protocol-create 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 1mo 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 — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create a Custom Protocol
Fork one of the built-in (system) protocols into team-management/protocol-configs/custom/ so you can edit its steps, modes, funcs, and step text freely. The engine resolves custom/ over system/, so your fork takes effect immediately — no further wiring needed.
Workflow
-
List the available protocols. Call
mcp__plugin_team-management_tm__protocol_list(). For each protocol, present to the user:- its name and one-line description, and
- its steps in order — each step's
name,mode, anddescription(from thestepsfield),
so the user understands how the protocol works and can choose which one to take as a base / rewrite.
-
If the user passed a protocol name as the argument, confirm it appears in the list, then skip to step 4 with that choice.
-
Otherwise ask which protocol to fork with
AskUserQuestion— one option per protocol, the optiondescriptionsummarizing what that protocol does. (The widget appends an "Other" option automatically — do not add one.) -
Fork it. Call
mcp__plugin_team-management_tm__protocol_customize(protocol_name="<choice>").- If the result lists files under
skipped, a previous fork already exists; those files were preserved. Tell the user, and only re-run withforce=Trueon their explicit confirmation (it overwrites their edits).
- If the result lists files under
-
Report the
created(and anyskipped) file paths plus thenext_stepstext. Tell the user to edit the copied files underteam-management/protocol-configs/custom/, and that the engine now resolves their custom versions over system automatically.
Rules
- Do NOT read or edit files under
team-management/protocol-configs/system/— it is a protected path; the MCP tool reads it for you inside the server process. - Do NOT try to copy protocol files with Bash/Edit/Write —
sessions-enforceblocks reads ofsystem/. Onlyprotocol_customize(MCP server, hook-exempt) can do the copy. - After a future team-management reinstall, run
/team-management:custom-protocol-update-after-reinstallto reconcile upstream changes against your fork.
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.
- 1mo ago First seen · 28 lines · 12 tokens per session scan A 23c07cbfd039
custom-protocol-create is a command published in the GitHub repository TeamManagementPlugin/claude-plugin (6 stars, last pushed 2d ago), licensed MIT. It adds 12 tokens to every session and 520 once invoked, about $0.0000 per session on Opus 5.5. 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 commands, from other repositories
sdd
Spec-driven dev loop. Plan once, then dev↔test↔eval loop until PRP spec satisfied. Local only, no PR.
golden-path
The golden path. One command, idea to merged PR. Runs the full pipeline, prd → prp → plan → dev → test → pr, with sensor + eval gates at every stage.
pack
Pack target repo with repomix. Snapshot for AI context. Cached per featureid.
dashboard
Build a shareable HTML dashboard of your hunt — funnel, status, categories, recruiter scores — from the tracker.
p4-sprint
Plans the current sprint: pulls matching stories from the backlog, defines the sprint goal, identifies risks, and creates the sprint document. Called repeatedly at the start of each new sprint.
continue
Resume the active pipeline at the next pending stage.