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 wahidyankf/ose-public --skill agent-developing-agentsgit clone --depth 1 https://github.com/wahidyankf/ose-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/wahidyankf/ose-public/agent-developing-agents)<a href="https://agentmods.dev/skills/wahidyankf/ose-public/agent-developing-agents"><img src="https://agentmods.dev/badge/skills/wahidyankf/ose-public/agent-developing-agents/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/wahidyankf/ose-public/agent-developing-agents"><img src="https://agentmods.dev/badge/skills/wahidyankf/ose-public/agent-developing-agents.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 | $0.00030 | $0.00979 |
| Opus 5.5 | $0.00012 | $0.00392 |
| Sonnet 5.5 | $0.00006 | $0.00196 |
| Haiku 4.5 | $0.00003 | $0.00098 |
Grade A, and why
agent-developing-agents 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 2d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Developing AI Agents
Comprehensive guidance for creating AI agents following repository conventions.
Core Requirements
- Frontmatter: name, description, tools, model, color, skills
- Name must match filename exactly
- Non-empty skills field required
File Operations in Binding Directories
Use normal file-editing tools only on paths that repo-config.yml classifies as source or
vendored. Platform authorization permits access; it does not override ownership. Never hand-edit
a generated path or generated delimited region. Bulk substitution is appropriate only for
mechanical changes within editable paths.
Canonical agent and skill sources live under .agents/agents/ and .agents/skills/; every
.claude/agents/ file is a generated route, never hand-authored. After editing a canonical
source, run ./rhino harness adapters generate; every changed mirror MUST land in the same
commit as its source. Verify with ./rhino harness adapters validate, which covers all registered
harnesses; the harness-adapters gate also runs it at pre-commit and pull request. No hook or gate
runs generate for you.
Edit a vendored path in place only when the registry assigns that class; see
the two vendored subclasses.
See also File-Touch Discipline.
References
Tool Usage Documentation
Agents with 4+ tools, unusual tool combinations, or non-obvious tool choices should document a "Tools Usage" section listing each tool and its purpose, placed after the core responsibility and before detailed workflow sections. See Tool Usage Documentation for the pattern and worked examples by agent family (checker/fixer/maker).
When to Use This Agent
Agents with overlapping scope or that users might confuse should include a "When to Use This Agent" section with "Use when" / "Do NOT use for" subsections, placed early in the file. See When to Use This Agent Pattern for the pattern, worked examples by agent family, and placement guidance.
What ships with it
6 files 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.
- 2d ago First seen · 73 lines · 30 tokens per session scan A 5b0d84e7c320
agent-developing-agents is a skill published in the GitHub repository wahidyankf/ose-public (12 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 979 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 2026-10-14.
Other skills, from other repositories
add-a-lib
Scaffold a new shared library under libs/ in the builders-stack monorepo. Use when code is needed in two or more places (apps or services) and should become a single source of truth consumed by package name. Covers the package.json, tsconfig, the one-public-door src/index.ts barrel, and wiring it into a consumer…
implement
Implement an agreed issue or spec through implementation, review, fixes, and a PR ready to merge.
triage
Classify an issue, identify missing information, and decide whether bounded automatic work is safe.
record-gotchas
Capture surprises, workarounds, and rough edges hit while consuming the public surface of Prisma 8, Prisma Compute, or Prisma Postgres — anything a real user of these products would experience. Fires whenever an operator (or agent) writes a workaround, hits a surprising failure mode, or finds undocumented behaviour…
resolution_playbook
How to choose one resolution action from a ticket and its customer history.
stacking-prs
Create and manage GitHub native Stacked PRs in this repo with the gh stack CLI. Use when asked to stack PRs, split a large change into a stack, add a layer to a stack, restack or rebase a stack, adopt existing branches or PRs into a stack, check out someone else's stack, or land a stack. Covers creating and submitting…