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 agentmods add skills/dirtybits/agent-skills/software-development-workflowsnpx skills add dirtybits/agent-skills --skill software-development-workflowsgit clone --depth 1 https://github.com/dirtybits/agent-skillsWhat 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 | $0.00044 | $0.01750 |
| Opus 5 | $0.00022 | $0.00875 |
| Sonnet 5 | $0.00009 | $0.00350 |
| Haiku 4.5 | $0.00004 | $0.00175 |
Grade A, and why
software-development-workflows 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Software Development Workflows
Overview
This umbrella covers the class-level software engineering practices that guide code work: planning, root-cause debugging, test-driven development, interactive debuggers, pre-commit review, simplification, and throwaway spikes.
It does not replace project-specific instructions. Always inspect the repository, its tests, and its conventions before applying generic recipes.
When to Use
- Debug failing tests, runtime bugs, build failures, or integration issues.
- Write tests before fixes or features.
- Use Python
pdb/debugpyor Node--inspectfor interactive diagnosis. - Run a pre-commit review or simplify a change set.
- Validate an uncertain technical approach with a spike.
- Author or adjust Hermes skill files.
Do not touch protected slash-command skills such as plan; when planning only, use the protected planning entry point if available.
Core Workflow
- Inspect before editing. Read relevant files, errors, configs, and tests.
- Reproduce. Run the smallest failing command and capture real output.
- Choose practice. Debugging, TDD, debugger attachment, review, simplification, or spike.
- Make minimal changes. Avoid broad refactors while fixing root causes.
- Verify. Run targeted tests first, then broader checks appropriate to the repo.
- Summarize with evidence. Report commands run, outputs, files changed, and residual risk.
Labeled Subsections from Former Narrow Skills
Systematic debugging
- No fixes before root cause. Read errors completely, reproduce, inspect recent changes, trace data flow, then form one hypothesis.
- If three attempted fixes fail, stop and question architecture instead of stacking a fourth patch.
Test-driven development
- RED: write or expose a failing test for the behavior.
- GREEN: implement the smallest root-cause fix.
- REFACTOR: clean only after tests prove behavior.
Python and Node debuggers
- Python: prefer targeted
pdb/debugpybreakpoints after reproducing the failure; avoid sprinkling permanent prints. - Node: use
--inspect/Chrome DevTools protocol only when normal logs/tests are insufficient; verify the debug target and port.
What ships with it
9 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.
- index.md 242 B
- LICENSE.txt 1.0 KB
- references/absorbed-packages/hermes-agent-skill-authoring/SKILL.original.md 7.8 KB
- references/absorbed-packages/node-inspect-debugger/SKILL.original.md 11 KB
- references/absorbed-packages/python-debugpy/SKILL.original.md 13 KB
- references/absorbed-packages/simplify-code/SKILL.original.md 8.7 KB
- references/absorbed-packages/spike/SKILL.original.md 8.9 KB
- references/absorbed-packages/systematic-debugging/SKILL.original.md 11 KB
- references/absorbed-packages/test-driven-development/SKILL.original.md 9.7 KB
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 · 112 lines · 44 tokens per session scan A 723bff33c00d
software-development-workflows is a skill published in the GitHub repository dirtybits/agent-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 1,750 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
Git PR Workflow
End-to-end workflow for creating a clean, reviewed pull request from a feature branch.
Git PR Workflow
End-to-end workflow for creating a clean, reviewed pull request from a feature branch.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
verify-security
安全校验关卡。自动扫描代码安全漏洞，检测危险模式，确保安全决策有文档记录。当用户提到安全扫描、漏洞检测、安全审计、代码安全、OWASP、注入检测、敏感信息泄露时使用。在新建模块、安全相关变更、攻防任务、重构完成时自动触发。.
development
开发语言能力索引。Python、Go、Rust、TypeScript、Java、C++、Shell。当用户提到编程、开发、代码、语言时路由到此。.
post-build-flow
Handles workflow verification and setup after build-workflow succeeds, or when the message contains workflow-verification-follow-up or workflow-setup-required. Load after direct builds, when verificationReadiness requires action, or on orchestrator verify/setup follow-up turns.