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 instructions/bomly-dev/bomly-cli/agents-mdgit clone --depth 1 https://github.com/bomly-dev/bomly-cliWhat 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 | $0.07006 | $0.07006 |
| Opus 5 | $0.03503 | $0.03503 |
| Sonnet 5 | $0.01401 | $0.01401 |
| Haiku 4.5 | $0.00701 | $0.00701 |
Grade A, and why
bomly-cli AGENTS.md 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- bomly-cli CLAUDE.md — 94% identical, 4 lines differ
How it starts
The opening of the file, as written. The whole thing — 336 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions — Bomly CLI
Guidance for AI agents working in this repository.
Bomly is a customer-facing, security-sensitive CLI for dependency intelligence. Audience: professional developers, security managers, and CI workflows. Expect high standards: correct behavior, clear output, full logging, and no panics.
This is the main public repository for the Bomly CLI: the engine, auditors, and native detectors (internal/*), the cmd/bomly entry point, user documentation (docs/), release automation, install scripts, the npm MCP wrapper, and the binary-driven smoke test suite. Two kinds of modules live outside this repository:
github.com/bomly-dev/bomly-sdk(public, separate repo): the contract both built-in components and external managed plugins implement — domain types, plugin kinds, validation, support metadata, and the shared helper subpackages (system,filecache,logkit,detectorkit,matcherkit,testkit). It has its own tests and releases; this repo pins released versions. Any reference tosdk.<Type>below means that module. Plugin authors start there, withdocs/PLUGINS.md,docs/plugins/, and the public plugin template repo.github.com/bomly-dev/bomly-plugin-*(public, one repo per component): external-integration components consumed as ordinary pinned Go modules — the four reachability analyzers (govulncheck,jsreach,pyreach,jvmreach), theosv/depsdev-license/scorecard/grypematchers, and thesyftdetector. Their implementations are NOT underinternal/; changes to them happen in their repos, and Dependabot bumps the pins here. Auditors and all other detectors are Bomly's own logic and stay in this repository.
Build & Test
make build # build both `bin/bomly` (builtin Syft/Grype) and `bin/bomly-lite`
make build-lite # go build -tags "bomly_external_syft,bomly_external_grype" -o bin/bomly-lite ./cmd/bomly
make test # go test ./...
make smoke # end-to-end tests driving the built binary (slow, requires network)
make smoke ARGS="-update" # regenerate smoke golden files
make fuzz FUZZTIME=5s # run every registered fuzz target with a short per-target budget
make benchmark # run the hidden local dependency-graph benchmark
make benchmark-report # analyze local benchmark artifacts with Copilot CLI
make evidence # verify the public evidence catalog (test/evidence/cases.json)
make run ARGS="scan" # go run ./cmd/bomly <ARGS>
make generate # regenerate config reference, JSON schemas, schema docs, support matrix, and component docs (binary-driven)
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 · 336 lines · 7,006 tokens per session scan A f051e42c3347
bomly-cli AGENTS.md is an instructions file published in the GitHub repository bomly-dev/bomly-cli (11 stars, last pushed 2d ago), licensed Apache-2.0. It adds 7,006 tokens to every session, about $0.0350 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 2026-08-31.
Other instructions, from other repositories
kc-secure-repo-template AGENTS.md
AGENTS.md instructions for CaseyLabs/kc-secure-repo-template, covering agents.md, project overview, project defaults, public interface and skill routing.
gh-guard CLAUDE.md
Instructions for sbom-tool/gh-guard, covering gh-guard: ci/cd supply chain hardening for rust, what this plugin does, hardening levels, commands and skills (contextual knowledge).
kc-secure-repo-template CLAUDE.md
Claude Code instructions for CaseyLabs/kc-secure-repo-template, a project described as: Security-hardened GitHub repository template, designed to prevent supply-chain attacks. Includes vulnerability scanning and AI agent skills.
Tracely-ai CLAUDE.md
Claude Code instructions for Jwuthri/Tracely-ai, covering claude.md, commands, architecture, hard rules and gotchas.
devopness AGENTS.md
Instructions for devopness/devopness, covering agents, core flow, shared constraints, monorepo structure and git workflow.
devopness CLAUDE.md
Instructions for devopness/devopness, a project described as: Devopness: AI DevOps on your cloud. Deploy apps, infra and CI/CD. Any cloud and any stack, one MCP. Deterministic API, opinionated and fully configurable. No cloud credentials in AI chats. Free plan.