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/sbom-tool/gh-guard/generategit clone --depth 1 https://github.com/sbom-tool/gh-guardWrote 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/sbom-tool/gh-guard/generate)<a href="https://agentmods.dev/commands/sbom-tool/gh-guard/generate"><img src="https://agentmods.dev/badge/commands/sbom-tool/gh-guard/generate.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 | $0.00010 | $0.01622 |
| Opus 5 | $0.00005 | $0.00811 |
| Sonnet 5 | $0.00002 | $0.00324 |
| Haiku 4.5 | $0.00001 | $0.00162 |
Grade A, and why
generate 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 4d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/generate — Single File Generator
Generate a single supply chain security config file from a template, with auto-detected project values.
Usage
/generate <target>
Available Targets
| Target | Template | Output Path |
|---|---|---|
ci-workflow |
templates/workflows/ci.yml |
.github/workflows/ci.yml |
publish-workflow |
templates/workflows/publish.yml |
.github/workflows/publish.yml |
codeql |
templates/workflows/codeql.yml |
.github/workflows/codeql.yml |
scorecard |
templates/workflows/scorecard.yml |
.github/workflows/scorecard.yml |
fuzz |
templates/workflows/fuzz.yml |
.github/workflows/fuzz.yml |
deny-toml |
templates/deny.toml |
deny.toml |
rust-toolchain |
templates/rust-toolchain.toml |
rust-toolchain.toml |
dependabot |
templates/dependabot.yml |
.github/dependabot.yml |
security-md |
templates/SECURITY.md |
SECURITY.md |
release-script |
templates/release.sh |
scripts/release.sh |
osv-scanner |
templates/osv-scanner.toml |
osv-scanner.toml |
Workflow
Step 1: Parse Target
Parse the argument to determine which template to use. If no argument or invalid target, show the available targets table above and ask the user to choose.
Step 2: Auto-Detect Values
Read project files to fill in placeholders:
| Placeholder | Detection Method (prefer cargo metadata, fall back to parsing) |
|---|---|
{{CRATE_NAME}} |
cargo metadata --no-deps --format-version=1 | jq -r '.packages[0].name' — fallback: sed -nE 's/^name = "([^"]+)"/\1/p' Cargo.toml | head -1 |
{{MSRV}} |
cargo metadata --no-deps --format-version=1 | jq -r '.packages[0].rust_version // empty' — fallback: sed -nE 's/^channel = "([^"]+)"/\1/p' rust-toolchain.toml |
{{REPO_OWNER}} |
`git remote get-url origin | sed -E 's |
{{REPO_NAME}} |
`git remote get-url origin | sed -E 's |
{{CONTACT_EMAIL}} |
cargo metadata --no-deps --format-version=1 | jq -r '.packages[0].authors[0]' | sed -E 's/.*<([^>]+)>.*/\1/' — fallback: ask user |
{{FUZZ_TARGETS}} |
Parse fuzz/Cargo.toml for [[bin]] name = "..." entries |
{{WORKSPACE_CRATES}} |
cargo metadata --no-deps --format-version=1 | jq -r '[.packages[] | select(.publish != false)] | sort_by(.dependencies) | .[].name' — filtered by publishable crates, in dependency order |
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.
- 4d ago First seen · 143 lines · 10 tokens per session scan A 7947d6470c6d
generate is a command published in the GitHub repository sbom-tool/gh-guard (15 stars, last pushed 5mo ago), licensed MIT. It adds 10 tokens to every session and 1,622 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
bob-update
Run the installed Hacker Bob update workflow for this project.
bob-export
Create a Hacker Bob post-release improvement bundle for the currently installed Bob version.
scope
Prepare a focused analysis scope for large codebases or monorepos using repomix. Creates a digestible snapshot of the target code for subsequent security analysis.
scan
Run automated static analysis and write the results to .claude/findings.json.
mobile-audit
End-to-end mobile audit driver for Android targets. Most Android bug-bounty work involves a decompiled APK that's been split into two directories.
auto-fix
Automatically generate and apply patches for verified security findings. Uses the patch-advisor agent to create context-aware fixes.