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 skills add DevInder1/supply-chain-scanner-public --skill scan-fullgit clone --depth 1 https://github.com/DevInder1/supply-chain-scanner-publicWrote 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/devinder1/supply-chain-scanner-public/scan-full)<a href="https://agentmods.dev/skills/devinder1/supply-chain-scanner-public/scan-full"><img src="https://agentmods.dev/badge/skills/devinder1/supply-chain-scanner-public/scan-full.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 5.1 | $0.00084 | $0.00597 |
| Opus 5 | $0.00042 | $0.00298 |
| Sonnet 5 | $0.00017 | $0.00119 |
| Haiku 4.5 | $0.00008 | $0.00060 |
Grade A, and why
scan-full 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 7d 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.
What it actually says
Full workspace scan
When the user wants comprehensive coverage — project + system + IDE — or mentions any of: "my whole machine", "my system", "Homebrew", "apt packages", "VS Code extensions", "JetBrains plugins", "IDE security", "audit everything":
- Call the tridentchain MCP tool
scan_fullwith:project_path= workspace root (absolute path)output_dir=.tridentchain-out-fullrun_profile="full"max_findings= 30
- Report findings grouped by source — this is the key value of
scan_full:- Project (npm/PyPI) —
raw_summary.vulnerability_breakdown_by_type.project - System packages (brew, apt) —
raw_summary.vulnerability_breakdown_by_type.system - IDE extensions (VS Code, JetBrains) —
raw_summary.vulnerability_breakdown_by_type.extension
- Project (npm/PyPI) —
- Highlight critical system findings first. A critical CVE in
git,openssl, orffmpegon the user's machine outranks any project finding. Always surface these at the top with the exact upgrade command (brew upgrade git, etc.). - If any KEV-listed package is on the user's machine (system or project), call it out as URGENT.
- Report runtime —
scan_fullis slower thanscan_project(5–60 seconds depending on how many system components are installed).
Why this matters
Project-only scanners miss the most impactful CVEs. A recent example: many systems shipped with git 2.35.x which has 3 critical CVEs (CVE-2024-32002 and family). A project scanner won't find that — scan_full does. Same logic applies to freetype, giflib, ffmpeg, and the entire VS Code marketplace extension catalog.
CLI fallback
tridentchain-security --scan all --project-path . --output-dir .tridentchain-out-full
When NOT to use scan-full
- User explicitly says "project only" → use
scan - User wants the fastest possible answer → use
quick-scan - User wants to verify a fix → use
validate-fixes
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.
- 7d ago First seen · 37 lines · 84 tokens per session scan A 5a6f910fe164
scan-full is a skill published in the GitHub repository DevInder1/supply-chain-scanner-public (0 stars, last pushed 1mo ago), licensed MIT. It adds 84 tokens to every session and 597 once invoked, about $0.0004 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 skills, from other repositories
bob-egress
List, add, test, enable, disable, or remove Hacker Bob egress profiles from Codex.
bob-export
Create a Hacker Bob post-release improvement bundle for the currently installed Bob version.
analyzing-sbom-for-supply-chain-vulnerabilities
Parses Software Bill of Materials (SBOM) in CycloneDX and SPDX JSON formats to identify supply chain vulnerabilities by correlating components against the NVD CVE database via the NVD 2.0 API. Builds dependency graphs, calculates risk scores, identifies transitive vulnerability paths, and generates compliance reports.…
pipeline-report
A procedure for reporting the state of an amoCRM sales funnel, a set of stages that deals move through before they are won or lost. It groups deals by stage and value and checks how long they have been inactive.
complete-task
A workflow for completing or reassigning ELMA365 business-process tasks. ELMA365 is a business process management system in which tasks move a process from one step to the next.
gigachat-embeddings
A text-embedding workflow for GigaChat. Embeddings are numeric representations that let software compare meanings rather than only matching exact words.