ac-safety-harden-supply-chain-sec

ac-safety-harden-supply-chain-sec is a skill for Claude Code from WaterplanAI/agentic-config. It costs 54 tokens per session (19,778 once invoked), scanned C, original, MIT.

A workflow for delaying the use of newly released packages and reviewing package dependencies for supply-chain risks.

In plain words
What is it for?
Use it to configure release-age rules for npm, pnpm, yarn, bun, or uv projects, exclude selected packages, run guided setup, and apply optional security hardening.
Why use it?
It reduces the chance of installing a compromised or problematic package immediately after release.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; mentions subagents; names the AskUserQuestion tool.

Part of the agentic-config plugin — 49 skills, 1 plugin shipped together

Good fit Use it to configure release-age rules for npm, pnpm, yarn, bun, or uv projects, exclude selected packages, run guided setup, and apply optional security hardening.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/waterplanai/agentic-config/ac-safety-harden-supply-chain-sec
Install

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.

Any agent
npx skills add WaterplanAI/agentic-config --skill ac-safety-harden-supply-chain-sec
Clone the repo
git clone --depth 1 https://github.com/WaterplanAI/agentic-config

Made for: Claude Code.

Or install agentic-config, the plugin that ships this one along with the rest of its 49 skills, 1 plugin.

Wrote 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.

agentmods badge for ac-safety-harden-supply-chain-sec

README.md
[![agentmods](https://agentmods.dev/badge/skills/waterplanai/agentic-config/ac-safety-harden-supply-chain-sec/github.svg)](https://agentmods.dev/skills/waterplanai/agentic-config/ac-safety-harden-supply-chain-sec)
Your own site
<a href="https://agentmods.dev/skills/waterplanai/agentic-config/ac-safety-harden-supply-chain-sec"><img src="https://agentmods.dev/badge/skills/waterplanai/agentic-config/ac-safety-harden-supply-chain-sec/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.

agentmods 80×15 button for ac-safety-harden-supply-chain-sec

Your own site · 80×15
<a href="https://agentmods.dev/skills/waterplanai/agentic-config/ac-safety-harden-supply-chain-sec"><img src="https://agentmods.dev/badge/skills/waterplanai/agentic-config/ac-safety-harden-supply-chain-sec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 19,778 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 4 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00054 $0.19778
Opus 5 $0.00027 $0.09889
Sonnet 5 $0.00011 $0.03956
Haiku 4.5 $0.00005 $0.01978

Measured 12d ago against content hash 0483aa72fba7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade C, and why

ac-safety-harden-supply-chain-sec scanned grade C with 4 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 12d 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.

Downloads and executes remote codemediumSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

- Never recommend or run `curl | sh` / `curl | bash` installers.

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Recursive force deletemediumDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

cd .. && rm -rf .harden-test

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Never recommend or run `curl | sh` / `curl | bash` installers.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

result = subprocess.run(["ruff", "--version"], capture_output=True, text=True)
packages/pi-ac-safety/skills/ac-safety-harden-supply-chain-sec/SKILL.md · 1,866 lines

How it starts

The opening of the file, as written. The whole thing — 1,866 lines — stays where its author put it; the contents beside it link to each section on GitHub.

harden-supply-chain-sec

Harden software supply chain security by configuring minimum release age policies across package managers.

Invocation

/harden-supply-chain-sec [<manager>|auto] [global|project] [<duration>] [--exclude pkg1,pkg2] [--guided] [--harden]

Arguments

Arg Required Default Description
manager No auto One of: pnpm, yarn, bun, npm, uv, all, auto. auto detects from project. all = all detected managers.
scope No project global, project, or both. When global, skip project root detection; use manager-specific global config paths. When both, run project scope first, then global scope (two passes through Sections 4-8a).
duration No 7d Human-friendly: 7d, 24h, 1w, 72h, 3d. Default is 7 days.
--exclude No (none) Comma-separated package names. Per-manager semantics differ (see Section 9).
--guided No false Interactive mode: AskUserQuestion at each decision point. Args are pre-filled defaults, not skips.
--harden No false Enable post-config security hardening (Sections 11-13).

Behavior

  • You are a senior security engineer hardening supply chain configuration.
  • Always show dry-run before any writes. Never write without explicit confirmation.
  • Fail-open on errors: warn and skip, do not block the user.
  • Detection and dry-run phases are read-only. Do not install, enable, or update tooling during preflight.
  • Any install/update, audit-tool installation, or lockfile-regeneration command requires a separate explicit confirmation after the exact command is shown.
  • Never recommend or run curl | sh / curl | bash installers.
  • Be project-agnostic: no hardcoded paths, repos, or organization names.
  • If --guided is present, always enter guided mode regardless of other args.
  • If --harden is present, proceed to hardening gates after config writes.

CRITICAL: Execution Order

Read the full file on GitHub · 1,866 lines

Changes

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.

  1. 12d ago First seen · 1,866 lines · 54 tokens per session scan C 0483aa72fba7

Subscribe to this mod's changes

ac-safety-harden-supply-chain-sec is a skill published in the GitHub repository WaterplanAI/agentic-config (30 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 19,778 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 4 findings (downloads and executes remote code, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.