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 QuentinCody/interlinked-cli --skill interlinked-supply-chaingit clone --depth 1 https://github.com/QuentinCody/interlinked-cliWrote 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/quentincody/interlinked-cli/interlinked-supply-chain)<a href="https://agentmods.dev/skills/quentincody/interlinked-cli/interlinked-supply-chain"><img src="https://agentmods.dev/badge/skills/quentincody/interlinked-cli/interlinked-supply-chain/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.
<a href="https://agentmods.dev/skills/quentincody/interlinked-cli/interlinked-supply-chain"><img src="https://agentmods.dev/badge/skills/quentincody/interlinked-cli/interlinked-supply-chain.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 34 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00165 | $0.03240 |
| Opus 5.5 | $0.00066 | $0.01296 |
| Sonnet 5.5 | $0.00033 | $0.00648 |
| Haiku 4.5 | $0.00016 | $0.00324 |
Grade A, and why
interlinked-supply-chain 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.
How it starts
The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
interlinked-supply-chain — package installs are default-deny
In an Interlinked-guarded repo, every package install is blocked before it runs unless the
exact package is pre-approved on .interlinked/package-allowlist.json. The stance: any new
dependency is potentially malicious (a response to the npm/PyPI malware surge). You cannot
install your way out, and you cannot silently self-approve. When blocked, the correct move is
almost always to surface the need to the human, not to force-approve.
Two independent requirements for an install to pass: (a) the name is allowlisted AND (b)
the version is an exact pin ([email protected]). An approved name at a floating version (lodash,
lodash@^4, lodash@latest) is still blocked — a range can resolve to a newer, compromised
release.
PyPI names use standard canonical spelling: case-insensitive, with runs of -, _ and .
collapsed to -. PyYAML and pyyaml use the same grant. This does not authorize a different
version. Conflicting legacy aliases fail closed; an authorized add replaces aliases with one
canonical entry, and remove removes all aliases. Other ecosystems retain their own semantics.
tests readiness python --json only proposes already-approved exact install argv; it never
installs or adds an approval. Resolve missing grants through the existing operator boundary.
Load this when
- A package install was blocked with
[interlinked:supply-chain]. - Editing a manifest (
package.json,requirements.txt,pyproject.toml,Cargo.toml,go.mod,Gemfile,composer.json,*.csproj, …) to add a dep was refused. npm ci/ barenpm install/pip install -rfails a snapshot check.- You need to approve, snapshot, list, or verify allowlisted packages.
What gets blocked
| Action | Result | Why |
|---|---|---|
npm install left-pad (name not allowlisted) |
block | not approved |
npm install lodash / lodash@^4 / lodash@latest |
block | not an exact pin (range/tag) |
npm install [email protected] (allowlisted + pinned) |
allow | — |
npm install --registry https://evil.tld pkg / --index-url … |
block | custom registry bypasses signing |
npm install git+https://… / tarball URL / file: spec |
block | never auto-approved (bypasses registry) |
npm ci / bare npm install / pip install -r req.txt with no matching snapshot |
block | lockfile not snapshot-approved |
Edit package.json to add "evil": "^1" |
block | manifest-edit gate (a second, separate gate) |
npm uninstall x / version bump of an existing dep |
allow | nothing new enters |
npm install ./local-dir (local path) |
allow | in-workspace, version-controlled |
| install verb while the daemon is down | block (fail-closed) | a dead guard is a security failure |
What ships with it
1 file 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.
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 Changed · +21 lines 3662b96cd5a5
- 1mo ago Changed · +29 lines d0c3146afd40
- 1mo ago First seen · 135 lines · 165 tokens per session scan A 8b06f6ea648b
interlinked-supply-chain is a skill published in the GitHub repository QuentinCody/interlinked-cli (180 stars, last pushed yesterday), licensed MIT. It adds 165 tokens to every session and 3,240 once invoked, about $0.0007 per session on Opus 5.5. 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
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…