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 skills/cboone/agent-harness-plugins/pin-everythingnpx skills add cboone/agent-harness-plugins --skill pin-everythinggit clone --depth 1 https://github.com/cboone/agent-harness-pluginsWrote 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/cboone/agent-harness-plugins/pin-everything)<a href="https://agentmods.dev/skills/cboone/agent-harness-plugins/pin-everything"><img src="https://agentmods.dev/badge/skills/cboone/agent-harness-plugins/pin-everything.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 | $0.00170 | $0.06118 |
| Opus 5 | $0.00085 | $0.03059 |
| Sonnet 5 | $0.00034 | $0.01224 |
| Haiku 4.5 | $0.00017 | $0.00612 |
Grade A, and why
pin-everything 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 — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pin Everything
Pin every version surface in a repository as a one-shot supply-chain hardening pass: SHA pins for actions, integrity hashes for Corepack, exact pins for package-manager dependencies (in application context), version-file refs for language runtimes, and explicit versions for install commands. Optionally generates a weekly drift-audit script and tightens Dependabot.
This skill is a generalization of the canonical hardening pass executed in PR #250 on agent-harness-plugins itself. Adopters who want to repeat that pass on their own repositories run the skill end-to-end. Adopters who only want a subset (for example, SHA-pinning actions) can stop after the relevant step.
Workflow
1. Audit the Repo for Version Surfaces
Scan the working tree for every version surface, then output a categorized table (file paths, count of refs, current pin state).
Surfaces to detect:
| Category | Detection |
|---|---|
GitHub Actions uses: refs |
Glob .github/workflows/*.{yml,yaml} and .github/actions/**/action.{yml,yaml}; also grep **/*.md for uses: lines (scaffolded reference docs and templates often embed real refs); grep for uses: |
| Reusable workflow refs | Same files plus the same Markdown sweep; grep for uses: lines containing .github/workflows/ |
packageManager field |
Read package.json; check .packageManager |
package.json deps |
Read package.json; flag ^/~ ranges in dependencies/devDependencies. Skip peerDependencies — see step 6. |
| Language version files | Glob .tool-versions, .nvmrc, .node-version, .ruby-version, .python-version, rust-toolchain.toml, build.zig.zon; also grep Gemfile for a ruby directive |
go.mod go directive |
Read go.mod; capture the directive line |
| Inline language pins in CI | Grep workflows for node-version:, ruby-version:, go-version:, python-version:, zig-version: (without -file suffix) |
go install pins |
Grep for go install <path>@<ref> where <ref> is latest, a vN.Y.Z tag (with optional prerelease), or a pseudo-version (v0.0.0-YYYYMMDDhhmmss-<12-hex>) |
cargo install pins |
Grep for cargo install with or without --locked --version |
pip / uv pins |
Grep for pip install, uv pip install, uv add, uv tool install, uvx (with or without ==) |
npx pins |
Grep for npx <name> (with or without @version) |
| Schema URLs | Grep *.json and *.yaml for $schema URLs containing @latest. Pinning is per-publisher (see step 7). |
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/checklist.md 15 KB
- references/dependabot.md 5.9 KB
- references/github-actions.md 5.5 KB
- references/install-commands.md 11 KB
- references/language-runtimes.md 14 KB
- references/scripts/version-audit-template 33 KB
- references/scripts/version-audit-workflow-template.yml 6.5 KB
- references/version-audit.md 20 KB
- references/yarn-corepack.md 6.7 KB
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 · 225 lines · 170 tokens per session scan A a14904dd2589
pin-everything is a skill published in the GitHub repository cboone/agent-harness-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 170 tokens to every session and 6,118 once invoked, about $0.0009 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
feature-spec
Creates a complete product feature specification with acceptance criteria, scope, dependencies, and risks. Delegates to the Prometeo (PM) agent.
implement-feature
Implements a feature from its specification. Reads the spec, designs architecture, writes code and tests. Delegates to the Forja (Dev) agent.
best-practices
Searchable knowledge base of 152+ programming best practices across 30+ languages and frameworks. BM25-powered search over curated resources from industry leaders (Google, Airbnb, Uber, Mozilla, Shopify, OWASP).
aidd-context:04:mermaid
Generate high-quality Mermaid diagrams from markdown content using a structured plan-validate workflow.
aidd-dev:06:refactor
Optimize code for performance and fix security vulnerabilities following OWASP guidelines.
aidd-context:03:context-generate
Generate Claude Code context artifacts - skills (router-based: SKILL.md + atomic testable actions + minimal evals), agents, and rules. Use when the user wants to create, refactor, add or remove actions in a skill, migrate a slash command into a skill, or generate a new agent or rule. Do NOT use for editing a single…