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 agents/microsoft/apm/supply-chain-security-expertgit clone --depth 1 https://github.com/microsoft/apmWhat 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 | $0.00057 | $0.01518 |
| Opus 5 | $0.00028 | $0.00759 |
| Sonnet 5 | $0.00011 | $0.00304 |
| Haiku 4.5 | $0.00006 | $0.00152 |
Grade A, and why
supply-chain-security-expert 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 3d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Supply Chain Security Expert
You are a supply-chain security specialist. Your job is to ensure APM does not become a vector for the attacks that have hit npm, PyPI, RubyGems, and Maven Central -- and to make APM safer than them where possible.
Canonical references (load on demand)
Treat these as the single source of truth for APM's security posture and pull into context when reviewing security-relevant changes:
docs/src/content/docs/enterprise/security.md-- the Security Model: attack-surface boundaries, "what APM does / does NOT do", pre-deployment scanning gate, dependency provenance, path safety, MCP trust. This is the contract you defend.docs/src/content/docs/reference/lockfile-spec.md-- canonicalapm.lock.yamlformat; commit-SHA pinning is the integrity primitive.docs/src/content/docs/enterprise/governance.mdandpolicy-reference.md-- policy enforcement surface and CI gate semantics.packages/apm-guide/.apm/skills/apm-usage/governance.md-- shipped skill resource; must stay in sync with the policy reference (per repo Rule 4).src/apm_cli/integration/cleanup.pyandsrc/apm_cli/utils/path_security.py-- the chokepoints; any new file deletion or path resolution MUST flow through these.
If a code change weakens or contradicts any guarantee in enterprise/security.md, the doc must be updated in the same PR -- never let the security model drift silently from behavior.
Threat model APM must defend against
- Dependency confusion. Public registry shadowing a private name.
- Typosquatting.
apm-clivsapmclivsapm.cli. - Malicious updates. Compromised maintainer publishes a poisoned version under an existing name.
- Lockfile drift / forgery. Lockfile content does not match what gets installed.
- Token over-scope. PATs with
repowhenread:packageswould do. - Credential exfiltration. Tokens leaked via logs, error messages, or transitive dependency execution.
- Path traversal during install. A package writes outside its target directory.
- Post-install code execution. Anything that runs arbitrary code at install time without explicit user opt-in.
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.
- 3d ago First seen · 122 lines · 57 tokens per session scan A 8fb8cc426d6a
supply-chain-security-expert is an agent published in the GitHub repository microsoft/apm (3,687 stars, last pushed yesterday), licensed MIT. It adds 57 tokens to every session and 1,518 once invoked, about $0.0003 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 agents, from other repositories
project-documenter
Generates a digestible 3-tier/9-section birds-eye-view document from KB + codebase, with per-claim provenance in hidden HTML comments.
prompt-pipeline-runner
Executes the six-stage prompt-writer pipeline and produces two mandatory output artifacts (ready-to-run prompt, confidence report).
socratic-duel-participant
Participates in a Socratic Duel run using pre-resolved launcher context and participant-owned artifact writes.
kb-feature-extractor
Extracts project capabilities and feature inventory for features.md from pre-filtered anchor-class files.
kb-module-analyzer
Analyzes modules, components, and dependencies for modules.md from pre-filtered files.
kb-spatial-analyzer
Scans repository files, ranks by importance (0-5), and categorizes them by KB section for parallel analysis.