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-harnessgit 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-harness)<a href="https://agentmods.dev/skills/quentincody/interlinked-cli/interlinked-harness"><img src="https://agentmods.dev/badge/skills/quentincody/interlinked-cli/interlinked-harness/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-harness"><img src="https://agentmods.dev/badge/skills/quentincody/interlinked-cli/interlinked-harness.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00149 | $0.12205 |
| Opus 5.5 | $0.00060 | $0.04882 |
| Sonnet 5.5 | $0.00030 | $0.02441 |
| Haiku 4.5 | $0.00015 | $0.01221 |
Grade D, and why
interlinked-harness scanned grade D 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 today.
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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
| **Destructive fs** | `rm -rf /`, `rm -rf *`, `rm node_modules`, `sudo rm …`, `dd`, `mkfs`, `shred`, `chmod 777` | `rm -rf /tmp/x`, `rm -rf dist/`, `rm -rf .wrangler/cache` | Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
quoted/heredoc/comment text, so *mentioning* `rm -rf /` in an `echo` is allowed while the Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| **Info-flow / persistence** | env exfil (`env \| curl …`, `printenv \| nc …`), `.npmrc`/`.yarnrc` writes, `nohup curl … &`, `crontab -e`, `systemctl enable`, writes to `/etc/cron.d/`, `*.service` | — | Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
no `child_process`/`subprocess`/`system`/`exec`. If the text can reach `sh`, `bash`, `eval`, How it starts
The opening of the file, as written. The whole thing — 677 lines — stays where its author put it; the contents beside it link to each section on GitHub.
interlinked-harness — the guard: what blocks you & how to respond
[interlinked:decision-metrics] is opt-in PostToolUse semantic advice. It can report
an adverse judgment, uncertainty, failure or missing evidence, but it never sets a
pre-execution block or authorizes an action. Both flags in
.interlinked/decision-metrics.json default off. The short inference deadline can
be followed by up to five seconds of local-model unload verification. Load
interlinked-quality-gates for configuration, replay and calibration; do not
weaken deterministic policy to satisfy a model's judgment.
Predict changes to guards
The prediction phase includes a local JS/TS if-ownership oracle, independent of
Supermodel and graph_prediction.enabled. Its default mode is shadow;
harness.guard_prediction.mode in shared .interlinked/config.json accepts
enforced, shadow (record/reveal without refusing), or off.
In the default shadow mode, review concise scope-change advice and relevant tests;
no declaration receipt is required. Repeated unchanged advice is deduplicated.
Only with explicit enforced policy, before intentionally changing which if
guards an existing return or throw, declare the expected ownership change.
The raw before/after AST comparison runs
before content checks; do not brace or format away an unexpected change.
Unpredicted changes block as protocol mismatches, not proven bugs. Correct the
proposal, or reconcile the exact revealed change with a rationale and behavioral
validation. A matching prediction does not prove correctness.
Receipts are JSON at .interlinked/predictions/guards/<sha256(session)>/<id>.json.
Fields: version: 1, session, id, file (canonical repository-relative path),
beforeSha256, afterSha256, nonce (nonempty declaration identifier), and
changes: an array of {owner, statement, before, after}. Statement and condition
strings use parser token spellings joined by spaces. Each guard is
{condition, branch: "then" | "else"}; arrays list outer to inner guards. The ID is
SHA-256 of JSON.stringify([1, file, beforeSha256, afterSha256]), with UTF-8 hashes
of the exact source bytes. Use the native session identity printed in a reveal.
The reveal includes the measured fields and receipt path. After a reveal, include
reconcile: id and a nonempty rationale; a late prediction alone cannot pass.
Identical retries retain their declaration; changed bytes, file or session require
a matching receipt. Never use a wildcard acknowledgment.
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.
- today Changed · +14 lines 79b730dd44b9
- 7d ago Changed · +149 lines aafe93f1b50f
- 28d ago Changed · +55 lines 292308c3808b
- 1mo ago Changed · +9 lines 7e168eda4587
- 1mo ago Changed · +20 lines bc37dc29a6a2
- 1mo ago Changed · +46 lines c747694927f8
- 1mo ago Changed · +104 lines 29a7f6d0844c
- 1mo ago Changed · +88 lines · -2 tokens per session e73dc7a31bd0
- 1mo ago First seen · 192 lines · 151 tokens per session scan D 44962653fdd3
interlinked-harness is a skill published in the GitHub repository QuentinCody/interlinked-cli (180 stars, last pushed yesterday), licensed MIT. It adds 149 tokens to every session and 12,205 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it D with 4 findings (asks for root, recursive force delete, makes network calls). 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…