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 MadAppGang/magus --skill team-gategit clone --depth 1 https://github.com/MadAppGang/magusWrote 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/madappgang/magus/team-gate)<a href="https://agentmods.dev/skills/madappgang/magus/team-gate"><img src="https://agentmods.dev/badge/skills/madappgang/magus/team-gate/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/madappgang/magus/team-gate"><img src="https://agentmods.dev/badge/skills/madappgang/magus/team-gate.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 | $0.00058 | $0.01648 |
| Opus 5.5 | $0.00023 | $0.00659 |
| Sonnet 5.5 | $0.00012 | $0.00330 |
| Haiku 4.5 | $0.00006 | $0.00165 |
Grade A, and why
team-gate 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Team gate: a gate is passed when its ballots have been read
The 2026-09-12 transcript audit (ai-docs/dev-workflow-gate-audit-2026-09-12.md) found
that team(mode="run") returning {"started": true} was being treated as the gate
passing, that panels which came back partial (1/4, 2/5 succeeded) were treated as
complete, and that gates were skipped without a word. This procedure closes all three.
Every gate site in /dev:dev, /dev:fix and /dev:audit follows it; none restates it.
The minimum ballot table
N is the number of external slots the gate launched. A ballot is a slot whose
status state is COMPLETED and whose response-<slot>.md matched require_pattern
(the settled status.summary counts these as succeeded). FAILED, EMPTY, still-RUNNING at
the poll ceiling, and never-started slots are not ballots.
| Gate | Where | MIN_BALLOTS |
|---|---|---|
| plan-review | /dev:dev Phase 3 Step 3.10 |
2 when N ≥ 3, otherwise N |
| code-review | /dev:dev Phase 5 Step 5.5, /dev:audit reviewer rows |
2 when N ≥ 3, otherwise N |
| verify | any verification panel (verify* session dirs) |
1 |
| fix-gate | /dev:fix Phase A and Phase B |
N (every launched slot) |
The internal reviewer (dev:architect, dev:reviewer, dev:debugger via the Agent
tool) is never a ballot in this count: it is always required, it is not covered by
require_pattern, and the phase's own rule says what a missing internal report means.
The procedure
1. Start with input_file only. Write the brief to <path>/prompt.md (or the gate's
named input file) and call:
team(mode="run", path=<gate dir>, models=[...], input_file=<gate dir>/prompt.md,
require_pattern=<the line the brief mandates>, min_output_bytes=400, agent=<if any>)
Never pass input beside input_file. The tool rejects the pair with
Pass input_file or input, not both, and the audit counted 32 gate calls lost to exactly
that. If the tool_result carries is_error with that text, retry ONCE with input_file
alone and nothing else changed. Any other error, or a second failure: the panel has
0 ballots. Record the error text and go to step 5.
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 · 119 lines · 58 tokens per session scan A fd6eab5efcfd
team-gate is a skill published in the GitHub repository MadAppGang/magus (13 stars, last pushed today), licensed MIT. It adds 58 tokens to every session and 1,648 once invoked, about $0.0002 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 2026-09-15.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…