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 Green-PT/honey-for-devs --skill honey-superpowersgit clone --depth 1 https://github.com/Green-PT/honey-for-devsWrote 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/green-pt/honey-for-devs/honey-superpowers)<a href="https://agentmods.dev/skills/green-pt/honey-for-devs/honey-superpowers"><img src="https://agentmods.dev/badge/skills/green-pt/honey-for-devs/honey-superpowers/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/green-pt/honey-for-devs/honey-superpowers"><img src="https://agentmods.dev/badge/skills/green-pt/honey-for-devs/honey-superpowers.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 | $0.00015 | $0.00875 |
| Opus 5 | $0.00008 | $0.00438 |
| Sonnet 5 | $0.00003 | $0.00175 |
| Haiku 4.5 | $0.00002 | $0.00088 |
Grade A, and why
honey-superpowers 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Honey × Superpowers
Honey is turned on by the session's SessionStart hook — which lives in your (the orchestrator's) context. Superpowers dispatches fresh subagents with isolated context; they never inherit the hook. So every implementer, reviewer, and fixer runs Honey-off: full-fat code (Lever 1 dark) and verbose reports (Lever 2 dark) — multiplied per dispatch. That's the leak. Close it by pasting the directive into the dispatch prompt itself.
The two skills already pull cost the same way Honey does — cheap model per task, file handoffs over pasted text, one-line narration. Don't fight them; stack on top. Honey adds what they don't: less code in the worker, terser reports both ways.
When it fires
Any time you are about to dispatch a subagent under a Superpowers-style workflow:
subagent-driven-development— implementer / task-reviewer / fixer per taskdispatching-parallel-agents— one agent per independent domainexecuting-plans— parallel-session execution- any orchestrator → worker handoff with isolated context
What to inject
On Claude Code with the Honey plugin, skip the paste: the plugin's
SubagentStart hook (hooks/honey-subagent.js)
injects the matching directive into every spawned subagent automatically
(reviewer-shaped agent types get the reviewer variant). The blocks below are for
other harnesses, or when the hook isn't installed.
Paste the matching block into the dispatch prompt body — inline text, not a Skill call (invoking burns a round-trip; the subagent only needs the rules).
Worker / implementer / fixer / parallel-domain agent:
Apply Honey: write the minimum code that needs to exist — YAGNI, stdlib/native
before custom; no speculative params, branches, or single-caller abstractions.
Never cut validation, error handling, auth, or anything the task asked for.
Keep code, identifiers, paths, and the brief's exact spec values verbatim.
Report terse: status, commits, one-line test summary, concerns. No narration.
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 · 87 lines · 15 tokens per session scan A afe9cdc74284
honey-superpowers is a skill published in the GitHub repository Green-PT/honey-for-devs (294 stars, last pushed 3d ago), licensed MIT. It adds 15 tokens to every session and 875 once invoked, about $0.0001 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
nft-standards
Implement NFT standards (ERC-721, ERC-1155) with proper metadata handling, minting strategies, and marketplace integration. Use when creating NFT contracts, building NFT marketplaces, or implementing digital asset systems.
postgresql-table-design
Use this skill when designing or reviewing a PostgreSQL-specific schema. Covers best-practices, data types, indexing, constraints, performance patterns, and advanced features.
spark-training-gotchas
Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.
parallel-feature-development
Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…
kpi-dashboard-design
Design effective KPI dashboards with metrics selection, visualization best practices, and real-time monitoring patterns. Use this skill when building an executive SaaS metrics dashboard tracking MRR, churn, and LTV/CAC ratios; designing an operations center with live service health and request throughput; creating a…
cost-optimization
Optimize cloud costs across AWS, Azure, GCP, and OCI through resource rightsizing, tagging strategies, reserved instances, and spending analysis. Use when reducing cloud expenses, analyzing infrastructure costs, or implementing cost governance policies.