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 curie-eng/curie --skill implementgit clone --depth 1 https://github.com/curie-eng/curieWrote 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/curie-eng/curie/implement)<a href="https://agentmods.dev/skills/curie-eng/curie/implement"><img src="https://agentmods.dev/badge/skills/curie-eng/curie/implement/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/curie-eng/curie/implement"><img src="https://agentmods.dev/badge/skills/curie-eng/curie/implement.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 | $0.00029 | $0.04743 |
| Opus 5.5 | $0.00012 | $0.01897 |
| Sonnet 5.5 | $0.00006 | $0.00949 |
| Haiku 4.5 | $0.00003 | $0.00474 |
Grade A, and why
implement 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 1mo 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 — 401 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement
Usage: /implement [ticket URL, ID, or description]
Use this as the default entry point for a ticket with clear acceptance criteria. Use the lightest process that can prove the requested behavior. Stop and ask for direction when the ticket cannot be read, its acceptance criteria are materially ambiguous, or implementation would require a decision outside the ticket.
Portable provider policy
Use the active environment for implementation. Do not require a particular agent, model, CLI, plugin, or hosted service.
If another independent provider is available locally, use it for a read only plan or diff review. Claude, Codex, and OpenCode are examples, not requirements. Keep execution with one provider and use another only to challenge the plan or completed diff. When no independent provider is available, use a fresh reviewer context in the active environment and state that the review was single provider.
Never install, configure, authenticate, or invoke a provider solely to satisfy this workflow. Never depend on home directory paths, custom profiles, personal hooks, metrics, queues, databases, background jobs, private credentials, or machine local helper scripts. Repository instructions and available tools are authoritative.
Setup
-
Read the ticket and its linked requirements. Do not infer scope from an ID alone.
-
Read the repository instructions and the relevant architecture or component docs.
-
Check for an existing branch or worktree for the ticket. If one exists, read
.projects/plans/<branch-name>.state.jsoninside it and resume from the stage it records rather than repeating finished work. See Run state below. Otherwise select the target release train before creating work:Work Base and PR target General bug, security fix, or shared change mainv0.7 feature or a bug unique to unreleased v0.7 work nextFetch the chosen base and create the worktree from its remote tip:
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.
- 1mo ago Changed · +8 lines 8a4d85ab6d82
- 1mo ago Changed · +35 lines 74d6cafed7c8
- 1mo ago First seen · 358 lines · 29 tokens per session scan A e16c50ec6ee7
implement is a skill published in the GitHub repository curie-eng/curie (37 stars, last pushed today), licensed Apache-2.0. It adds 29 tokens to every session and 4,743 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
remove-ai-slops
Removes AI-generated code smells from branch changes or an explicit file list behind regression tests. Use when the user asks to clean up, deslop, or remove AI-slop patterns from recent changes.
codex-ab
Run an A/B codex review experiment — holistic codex review vs 3 focused dimension passes (security, ecto, liveview) on the branch diff, classify findings, report a panel-value verdict. Use when the branch is fresh, before any codex review runs.
codex-loop
Fix Elixir/Phoenix code until Codex CLI review comes back clean — bounded review, fix, verify loop before opening a PR. Use when codex is installed and you want an external cross-model critic on your changes before pushing.
hermit-scribe
File a GitHub issue or post a comment on an existing issue via a GitHub App bot identity. Use when the operator says "file as a GH issue", "open an issue for PROP-NNN", "report this to the tracker", "add a comment to issue.
spike-consumer-adversarial
OI-3 spike harness — heavy consumer, ADVERSARIAL arm. Worst-case early-exit test: the mid-workflow Skill call has no continuation guardrail and the guidance skill ends with a final-sounding anchor. Use only when explicitly invoked by the spike harness with a TRIALID and data path.
general-best-practices
General software development best practices covering code quality, testing, security, performance, and maintainability across technology stacks.