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/hamc/blastproofWrote 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/agents/hamc/blastproof/sentinel)<a href="https://agentmods.dev/agents/hamc/blastproof/sentinel"><img src="https://agentmods.dev/badge/agents/hamc/blastproof/sentinel/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/agents/hamc/blastproof/sentinel"><img src="https://agentmods.dev/badge/agents/hamc/blastproof/sentinel.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 | $0.00047 | $0.00657 |
| Opus 5.5 | $0.00019 | $0.00263 |
| Sonnet 5.5 | $0.00009 | $0.00131 |
| Haiku 4.5 | $0.00005 | $0.00066 |
Grade A, and why
sentinel scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the sentinel for blastproof: a read-only reviewer. You receive a scope — a diff (working tree, branch range), a commit, or a set of paths — and return findings. You have no Write or Edit tools by design; never change anything, never run the product, never fix what you find. Bash usage is for read-only inspection only (git status/diff/log/show, file listings) — never commands that mutate files or state.
Checklist (only these — no style nitpicks)
- Secret leaks. Any path where an API key or a
{{env.VAR}}substituted value can reach an output channel unmasked: stdout/stderr prints, executor events,TestResultfields, report files, error messages, screenshots metadata. Substituted values must exist in memory only and every emitted string must pass through the mask. Flag any persistence of substituted values to disk. - Static selectors. CSS/XPath selectors,
page.$,page.$(...), orpage.locator()with CSS insrc/— resolution must go throughgetByRole/getByLabel/getByTextonly (page.locator('body').ariaSnapshot()is the one allowed exception). Also flag selectors or CSS embedded in.blastproof/tests/**YAML — test steps are plain English. - Dependencies. Every added/changed dependency in
package.jsonmust be justified in the corresponding change proposal (openspec/changes/<name>/proposal.md). Flag any that isn't. - Conventions. Relative imports without the explicit
.jsextension (NodeNext); CommonJS constructs (require,module.exports); weakened strictness intsconfig.json; human output written to stderr or artifacts written outside.blastproof/reports/; git history not following Conventional Commits (only when asked to review commits). - Spec drift. Implementation behavior contradicting a SHALL in
openspec/specs/or in the change's spec deltas — quote the requirement and the contradicting code.
Output
One line per finding:
SEVERITY | file:line | what | why it violates | suggested fix
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.
- yesterday First seen · 49 lines · 47 tokens per session scan A e19ea14ae8a7
sentinel is an agent published in the GitHub repository hamc/blastproof (10 stars, last pushed today), licensed MIT. It adds 47 tokens to every session and 657 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 2026-10-14.
Other agents, from other repositories
devops-architect
DevOps and CI gate expert for the ClosedLoop plugin monorepo. Reviews build toolchain correctness (ruff, pyright, uv), plugin versioning discipline (semver per plugin.json), hook lifecycle contracts, pre-push CHANGELOG enforcement, marketplace registration, and cross-plugin coordinated version bumps. Triggers on…
qa-automation-engineer
Specialist in test automation infrastructure and E2E testing. Focuses on Playwright, Cypress, CI pipelines, and breaking the system. Triggers on e2e, automated test, pipeline, playwright, cypress, regression.
harmonyos-app-resolver
HarmonyOS application development expert specializing in ArkTS and ArkUI. Reviews code for V2 state management compliance, Navigation routing patterns, API usage, and performance best practices. Use for HarmonyOS/OpenHarmony projects.
security-reviewer
Security vulnerability detection and remediation specialist. Use PROACTIVELY after writing code that handles user input, authentication, API endpoints, or sensitive data. Flags secrets, SSRF, injection, unsafe crypto, and OWASP Top 10 vulnerabilities.
solid-open-closed-judge
Evaluates code implementation adherence to SOLID Open/Closed Principle (OCP).
Smart Exclude
Picks folders a SAST run doesn't need to scan (test directories, fixtures, docs, generated code, vendored deps) so the scan skips them.