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 joao-aires/agent-skills-public --skill developgit clone --depth 1 https://github.com/joao-aires/agent-skills-publicWrote 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/joao-aires/agent-skills-public/develop)<a href="https://agentmods.dev/skills/joao-aires/agent-skills-public/develop"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/develop/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/joao-aires/agent-skills-public/develop"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/develop.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 | $0.00052 | $0.00911 |
| Opus 5.5 | $0.00021 | $0.00364 |
| Sonnet 5.5 | $0.00010 | $0.00182 |
| Haiku 4.5 | $0.00005 | $0.00091 |
Grade A, and why
develop 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 yesterday.
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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Develop
Read task guidance. Use system-design after product refinement or when the feature changes consequential architecture, before dependent planning/implementation. Read git-contributions for the objective's feature worktree, deliver-reliable-changes for verification and completion. Load the optional stack/domain guidance selected by task guidance only when relevant and available.
When starting a new application
Read new-application flow. Reuse sufficient accepted evidence and establish missing outcomes before work that depends on them:
- Purpose and business context.
- Product outcome and useful slice.
- Requirements and observable acceptance.
- Feasibility and system design.
- UX and visual direction.
- Implementation plan and foundations.
- Implementation, testing and repair.
- Delivery and learning.
A named stack or starter kit does not supply missing decisions. Defined existing work reuses accepted context; it does not restart the full lifecycle.
Establish a useful slice
Treat the rough idea as an outcome to shape, not an instruction to build every imagined feature. Inspect the repository and supplied references first.
- For a new product select a useful coherent first slice; for existing work preserve architecture, identity, UI and operations constraints.
- When users, product value or priorities are uncertain, use installed product discovery and prioritization expertise to establish the product decision before dependent requirements/design.
- Use business strategy when business direction or viability is actually unresolved.
- Reuse accepted context for defined work.
Resolve decisions before dependent work
Clarify material user/business outcomes, data/authority boundaries and high-impact UX/API/architecture choices before dependent work.
- Ask a small coherent set of decision-changing questions; retain answers already provided.
- State reversible assumptions for ordinary details and proceed within scope.
- In unattended mode return the concrete blocking decisions and useful independent findings instead of fabricating them.
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.
- yesterday Changed · +41 lines f7b606758683
- 2d ago Changed e1f5eb808ac9
- 3d ago Changed · -2 lines 23c834279036
- 5d ago Changed · +4 lines 19b5d80afb47
- 7d ago First seen · 26 lines · 52 tokens per session scan A efbb6f11c8e2
develop is a skill published in the GitHub repository joao-aires/agent-skills-public (2 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 911 once invoked, about $0.0002 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 2026-10-15.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.