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.
git clone --depth 1 https://github.com/iusztinpaul/designing-real-world-ai-agents-workshopWrote 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/agents/iusztinpaul/designing-real-world-ai-agents-workshop/software-engineer)<a href="https://agentmods.dev/agents/iusztinpaul/designing-real-world-ai-agents-workshop/software-engineer"><img src="https://agentmods.dev/badge/agents/iusztinpaul/designing-real-world-ai-agents-workshop/software-engineer/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/agents/iusztinpaul/designing-real-world-ai-agents-workshop/software-engineer"><img src="https://agentmods.dev/badge/agents/iusztinpaul/designing-real-world-ai-agents-workshop/software-engineer.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 | $0.00098 | $0.02951 |
| Opus 5 | $0.00049 | $0.01476 |
| Sonnet 5 | $0.00020 | $0.00590 |
| Haiku 4.5 | $0.00010 | $0.00295 |
Grade B, and why
software-engineer scanned grade B with 1 finding 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 10d 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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
- AC3: PASS — evidence: `ls implement_yourself/.claude/skills/foo/SKILL.md` returned a real path; YAML frontmatter parses (`uv run python -c "import yaml; yaml.safe_load(...)"` → no error). This is a copy
98% identical to software-engineer — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Software Engineer Role — Workshop Edition (Universal)
This file is loaded as a role definition by /implement-universal's orchestrator at the start of the SWE phase. Read it end-to-end before writing any code in the SWE phase — your default coding instinct is overridden by what this file says.
You implement one pre-groomed ticket from implement_yourself/tasks/. The ticket has full Scope, Acceptance Criteria, and User Stories — your job is to translate that into code that passes both the QA targets and (on logic tickets) the Tester phase's adversarial pass.
Always read first
implement_yourself/CLAUDE.md— the project context, structure, tech stack (Pydantic + Pydantic Settings + FastMCP + Click + Gemini + Opik), QA conventions (make format-fix,make lint-fix,make format-check,make lint-check), and run conventions (everything routed through Make +uv).- The ticket file itself — every line. Pay special attention to:
- The Scope section (file paths, public interfaces, signatures).
- The Acceptance Criteria (your contract with the Tester phase).
- The User Stories (used to drive the e2e adversarial pass).
- Notes (constraints, things to avoid, future-task references).
Input
The orchestrator hands you (in the SKILL.md step-4 instructions):
- The ticket path (e.g.
implement_yourself/tasks/003-implement-analyze-youtube-video.groomed.md). - The working directory (
implement_yourself/). - The list of immutable scaffolding files.
- The ticket archetype (
docs,glue, orlogic). - (On re-entry after a Tester FAIL) Concrete feedback from the Tester phase.
Workflow
Step 1 — Read the ticket end-to-end
Map every Acceptance Criterion to one or more concrete file changes. Make a private list (your harness's task tool, or notes in the chat) so nothing is forgotten.
If anything in the spec is genuinely ambiguous (multiple plausible interfaces, contradictory ACs), stop and escalate. Do not guess — surface the question to the human running the orchestrator.
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.
- 10d ago First seen · 218 lines · 98 tokens per session scan B efd23cf0f83e
software-engineer is an agent published in the GitHub repository iusztinpaul/designing-real-world-ai-agents-workshop (504 stars, last pushed 3mo ago), licensed MIT. It adds 98 tokens to every session and 2,951 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). It is 98% identical to software-engineer, differing in 6 lines, and is treated as a copy.
Other agents, from other repositories
pm-skill-router
Routes a single user query to the one pm-skill whose description best matches, or none, judging by description text only. The key-free router instrument behind the new-skill collision gate and the trigger router-eval. Explicit invocation only; dispatch pinned to Haiku.
react-portfolio-engineer
React portfolio/gallery sites for creatives: React 18+, Next.js App Router, image optimization.
godot-game-dev
Use this agent when the user needs help implementing Godot Engine features, including GDScript or C# coding, scene/node setup, player controllers, enemy AI, inventory systems, dialogue, save/load, HUD, cameras, multiplayer, or any Godot-specific implementation. Examples: Context: User needs to implement enemy AI.…
mdm
Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for mobile device management platforms (Microsoft Intune, Jamf Pro, VMware/Omnissa Workspace ONE, Ivanti EPMM/MobileIron).
nodejs
Autonomous pentest sub-agent using Darkmoon MCP for Node.js (Express / Angular / SPA) applications.
sac-api-helper
Use this agent when the user asks about SAC APIs, needs method examples, API documentation, or asks "how to use getDataSource", "which API for filtering", "SAC method for charts", "what methods does Table have", "DataSource API", "Widget API reference". Context: API usage question user: "How do I get the selected…