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 commands/whitelonng/dshcode/manteamgit clone --depth 1 https://github.com/whitelonng/dshcodeWrote 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/whitelonng/dshcode/manteam)<a href="https://agentmods.dev/commands/whitelonng/dshcode/manteam"><img src="https://agentmods.dev/badge/commands/whitelonng/dshcode/manteam.svg" alt="Measured on agentmods" 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 | $0.00008 | $0.01174 |
| Opus 5 | $0.00004 | $0.00587 |
| Sonnet 5 | $0.00002 | $0.00235 |
| Haiku 4.5 | $0.00001 | $0.00117 |
Grade A, and why
manteam 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 today.
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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mancode mode: manteam
Purpose: plan and execute work with explicit team ownership and handoff.
Enter through mancode
Before the first command, use ./node_modules/.bin/mancode when it exists, otherwise mancode; check that selected binary with --version once and never mix binaries or versions. In every command below, replace the literal mancode with that selected binary path when the local binary exists.
- Reuse a
mancode status --brief --jsonsnapshot already obtained in this conversation. Only when none exists, run it once from the project root. Never read or write the legacy authority file. - If
identity.actorIdis absent, ask for a display name and runmancode team identity create --name "<display name>". - Reuse
session.sessionIdwhen present. If status has no current session, reuse an explicit session ID already retained in this conversation. Only if neither exists, runmancode context session new --client cursorexactly once and retain the returned session ID. Use--client cursoron every command that uses this session. - Reuse the current TaskRef. To bind a supplied existing task, run
mancode context resume <namespace:ULID> --session <id> --client cursor. - For an existing task, read only the needed Context Pack with
mancode context show --purpose plan --session <id> --client cursor; include--task <namespace:ULID>when it is not yet bound. For a new task, create it through the mode action first, then read the returned TaskRef's Context Pack.
Mode action
- Confirm team membership with
mancode team status; join invited participants before assigning shared work. - Read
.mancode/shared/context/glossary.jsonwhen it exists and prefer its confirmed terms in shared requirements, plans, and handoffs. - For a new shared task, run
mancode workflow create manteam "<task>" --visibility shared --coordination team --confirm-shared --session <id> --client cursor. - Run the same bounded read-only discovery as
man, with at most F-1 through F-3 typed as premise, scope, technical, risk, or acceptance and marked asrepository_factordomain_hypothesis; an unverified domain hypothesis becomes a focused question, never a fact. Discovery produces evidence and recommendations, never execution authority. - Give every F-ID one type-directed disposition: Accepted scope or behavior findings enter
confirmedScopeand the matchingacceptanceCriteria; accepted technical choices entertechnicalDecisions; Only explicitly excluded behavior entersexcludedScope; low-impact reversible details may enterdefaults; an unaccepted proposal remains unauthorized without being copied into every field. - Apply the same decision-readiness gate as
manbefore finalizing requirements: validate both clarity and soundness against project facts and team authority. If the goal, scope, acceptance, owner/source of truth, and constraints are clear and consistent, continue without ceremonial questions; if a decision-changing ambiguity, ownership conflict, or hard-risk direction remains, give evidence and a recommendation, ask focused questions, and wait before writing confirmed requirements. - Persist unresolved team clarification through the same
workflow requirements <namespace:ULID> draft --file <requirements.json>command asman; do not leave ownership questions or partial answers only in chat history. - Bind the confirmed team plan to the user-visible
implementationScopethrough plan revise--scope-file; claims, edits, and review must stay inside include and outside exclude. Before editing, state material assumptions and verifiable success criteria, reuse existing code and dependencies, and make the smallest direct plan-traceable change; newly proposed behavior outside confirmed requirements requires read-onlyNEEDS_REALIGNMENTand operator-approved reframe. - If the operator explicitly approves a file-boundary-only adjustment that leaves confirmed behavior and acceptance unchanged, use
mancode workflow scope change <shared:ULID> --expected-revision <n> --file <scope.json> --session <id> --client cursor. It versions the plan authority, stales prior review/verification, and reissues compatible claims. Behavior or acceptance changes still require reframe. - Use claims, checkpoints, sync, and handoffs through
mancode team; never infer ownership from an adapter prompt. - With git-ref transport, workflow creation plus requirements, plan, review, and verification mutations use an explicit deferred publication boundary: run the workflow command without
--sync, commit the resulting.mancode/sharedauthority changes together with the matching code head, then runmancode team sync push <shared:ULID> --expected-task-revision <n>. Never report cross-clone synchronization before the push returns a receipt. Use--synconly for a command whose contract performs an atomic git-ref mutation. If that atomic mutation leaves tracked.mancode/sharedprojection changes for a resumable in-progress or blocked task, commit them, then run the sameteam sync pushwith the unchanged task revision to rebind the remote code head before another clone resumes the task.
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.
- today First seen · 37 lines · 8 tokens per session scan A d0da35109f2f
manteam is a command published in the GitHub repository whitelonng/dshcode (711 stars, last pushed today), licensed MIT. It adds 8 tokens to every session and 1,174 once invoked, about $0.0000 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 2026-09-03.
Other commands, from other repositories
build-parallel
Advance parallel Generator-side actions only. Auto-selects contract, build, or fix from status.md. /auto-harness:build-parallel [sprint].
qa-parallel
Advance parallel Evaluator-side actions only. Auto-selects review, QA, retest, or final report from status.md. /auto-harness:qa-parallel [sprint].
qa
Advance Evaluator-side actions only. Auto-selects review, QA, retest, or final report from status.md. /auto-harness:qa [sprint].
build
Advance Generator-side actions only. Auto-selects contract, build, or fix from status.md. /auto-harness:build [sprint].
sdlc
Route a task to the next synced SDLC workflow based on current artifacts and repo state.
dashboard-session-fork
Fork a session into a new one. Usage /dashboard:session-fork.