Borrowing it
Nothing to install: this file belongs to bredmond1019/claude-sdk-rs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bredmond1019/claude-sdk-rs/main/.agents/skills/run-the-gates/SKILL.mdgit clone --depth 1 https://github.com/bredmond1019/claude-sdk-rsWrote 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/bredmond1019/claude-sdk-rs/run-the-gates)<a href="https://agentmods.dev/skills/bredmond1019/claude-sdk-rs/run-the-gates"><img src="https://agentmods.dev/badge/skills/bredmond1019/claude-sdk-rs/run-the-gates/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/bredmond1019/claude-sdk-rs/run-the-gates"><img src="https://agentmods.dev/badge/skills/bredmond1019/claude-sdk-rs/run-the-gates.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 | $0.00108 | $0.01440 |
| Opus 5.5 | $0.00043 | $0.00576 |
| Sonnet 5.5 | $0.00022 | $0.00288 |
| Haiku 4.5 | $0.00011 | $0.00144 |
Grade A, and why
run-the-gates 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 11d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Running the gates
Paths below are relative to the brain root — the directory containing
brain.toml, found by walking up from wherever you are. This skill is synced into every repo, so a repo-relative link would be wrong in most of them.
Most wasted gate time here is not a broken gate. It is a true result to a question you did not mean to ask.
1. One flag per invocation — they do not compose
validate-brain's mode flags dispatch through an if/else-if chain with a fixed precedence:
--links > --structure > --state > --graph > --sync > (base)
Pass two and the loser is silently ignored — you get a real, passing result for a check you didn't run. Run them separately, always:
bastion validate-brain --structure # index.md <-> directory coverage
bastion validate-brain --links # dead markdown / file:// / [[wikilink]] targets
bastion validate-brain --graph # related: edge integrity
bastion validate-brain --state # state.json schema + cross-repo block graph
mev validate-brain has the same flags — bastion delegates to mev. HQ's planning/harness.json
gates on the bastion form; prefer it for consistency.
Other verbs do not share this shape: bastion brain / bastion code use a clap ArgGroup
(hard error), and syn queries uses an explicit parser.error. The silent-drop is specific to
validate-brain.
2. A piped command's $? is the pipe's, not the command's
mev conformance | tail -3 # prints failures, reports success
This has cost real runs. Redirect, then check:
mev conformance > /tmp/out.txt 2>&1; rc=$?; tail -3 /tmp/out.txt; echo "rc=$rc"
Same trap with | head, | grep, | jq. If you only need the tail of the output, still capture the
exit code separately.
3. A red gate is frequently not yours
Attribution is by delta, not by path (docs/decisions/D64-push-gate-delta-attribution.md): stage
1 of the push gate validates the whole corpus but blocks only on errors new since this clone's last
successful push. With several agents live, --structure in particular goes red because another
session added a file and has not written its index.md row yet.
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.
- 11d ago First seen · 118 lines · 108 tokens per session scan A 3398f3fc4293
run-the-gates is a skill published in the GitHub repository bredmond1019/claude-sdk-rs (23 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 108 tokens to every session and 1,440 once invoked, about $0.0004 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 2026-10-26.
run-the-gates compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| run-the-gatesbredmond1019/claude-sdk-rs | Skill | 23 | 1mo ago | Apache-2.0 | A | 108 | Claude Code, Codex |
| systematic-debuggingNousResearch/hermes-agent | Skill | 261k | yesterday | MIT | A | 16 | Claude Code, Codex |
| observability-langsmithdavila7/claude-code-templates | Skill | 33k | yesterday | MIT | A | 44 | Claude Code, Codex |
| experimental-code-coverage-local-debuggerchromium/chromium | Skill | 25k | yesterday | BSD-3-Clause | A | 59 | Claude Code, Codex |
| verify-omnigentomnigent-ai/omnigent | Skill | 11k | today | Apache-2.0 | A | 100 | Claude Code, Codex |
| cli-e2eComposioHQ/composio | Skill | 31k | yesterday | MIT | A | 62 | Claude Code, Codex |
| adversarial-revieweremdash-cms/emdash | Skill | 14k | yesterday | MIT | A | 72 | Claude Code, Codex |