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 ondrej-svec/heart-of-gold-toolkit --skill contractgit clone --depth 1 https://github.com/ondrej-svec/heart-of-gold-toolkitWrote 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/ondrej-svec/heart-of-gold-toolkit/contract)<a href="https://agentmods.dev/skills/ondrej-svec/heart-of-gold-toolkit/contract"><img src="https://agentmods.dev/badge/skills/ondrej-svec/heart-of-gold-toolkit/contract/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/ondrej-svec/heart-of-gold-toolkit/contract"><img src="https://agentmods.dev/badge/skills/ondrej-svec/heart-of-gold-toolkit/contract.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00073 | $0.01329 |
| Opus 5 | $0.00036 | $0.00665 |
| Sonnet 5 | $0.00015 | $0.00266 |
| Haiku 4.5 | $0.00007 | $0.00133 |
Grade A, and why
contract 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 11d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contract (review / manage evidence contracts)
A small, deliberate management surface for the per-task evidence contracts written by /quellis-architect:plan and consulted by the Stop hook. Reads by default; writes only on explicit subcommands. Authoring new contracts and editing claim shapes is /quellis-architect:plan's job — this skill exists for lifecycle bookkeeping.
Boundaries
This skill MAY: read .quellis/contracts/ files, print contract content, flip status to completed or abandoned on explicit subcommand, delete .quellis/contracts/active.toml when the active contract closes.
This skill MAY NOT: edit claim shapes, add or remove [[claim]] blocks, rewrite the pointer to a different task without an activate subcommand (not in V1.1), edit code, run tests.
To change what a contract claims, run /quellis-architect:plan again with the same brainstorm. That rewrites the contract cleanly. Mid-flight claim edits drift from the substrate V1.2 personalization compounds.
Common Rationalizations
| Shortcut | Why it fails | The cost |
|---|---|---|
| "Just edit claim_regex inline to make the gate pass" | The gate exists because the unrefined claim is dangerous. Tweaking the regex is laundering. | Silent regression on the next agent that inherits the lying contract. |
| "Mark abandoned to avoid the complete-prompt friction" | abandoned is for tasks dropped without finishing. Marking abandoned to skip evidence buries the trail. |
Lost compounding signal for V1.2. |
| "Skip showing the contract — the user knows what's active" | Memory drifts across sessions. A 30-second show is cheap insurance against the user assuming a stale contract. | Stop fires on something the user didn't realize was still active. |
Phase 0: Detect the subcommand
Entry: user invoked /quellis-architect:contract [subcommand] [args].
Subcommands:
| Subcommand | Args | Action |
|---|---|---|
show (default if no arg) |
none | Print the active contract; if none, say so. |
list |
none | Print every contract in .quellis/contracts/, marking which is active and each one's status. |
complete |
none | Mark the active contract status = "completed". Clear active.toml. Asks once to confirm. |
abandon |
none | Mark the active contract status = "abandoned". Clear active.toml. Asks once to confirm. |
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.
- 11d ago First seen · 125 lines · 73 tokens per session scan A 1935d96b8628
contract is a skill published in the GitHub repository ondrej-svec/heart-of-gold-toolkit (19 stars, last pushed 22d ago), licensed MIT. It adds 73 tokens to every session and 1,329 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…