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/crypticswarm/swarmforge/general-software-engineeringnpx skills add CrypticSwarm/Swarmforge --skill general-software-engineeringgit clone --depth 1 https://github.com/CrypticSwarm/SwarmforgeWhat 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 | $0.00042 | $0.00461 |
| Opus 5 | $0.00021 | $0.00230 |
| Sonnet 5 | $0.00008 | $0.00092 |
| Haiku 4.5 | $0.00004 | $0.00046 |
Grade A, and why
general-software-engineering 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
General Software Engineering
This skill defines baseline professional defaults for software engineering work. It is intentionally low precedence and exists to prevent common failure modes in automated coding.
Precedence
When guidance conflicts, follow this order:
- Explicit user instructions
- More specific task skills
- This skill
- Default agent behavior
This skill must yield to any more specific skill or clear user intent.
Core Defaults
Change Discipline
- Prefer the smallest viable change that satisfies the request.
- Avoid refactors, cleanups, or stylistic changes unless explicitly requested.
- Do not modify unrelated files, logic, or formatting.
Intent Preservation
- Follow existing patterns, abstractions, and conventions in the codebase.
- Do not redesign systems unless asked.
- Optimize for consistency with surrounding code over personal preference.
Safety Assumptions
- Assume changes may affect production unless clearly scoped otherwise.
- Be conservative around:
- Authentication and authorization
- Data persistence and migrations
- Configuration and environment handling
- Public APIs and contracts
- Ask before making changes that could introduce breaking behavior.
Testing & Verification
- Prefer existing tests; understand them before adding new ones.
- Add or update tests when behavior changes or bugs are fixed.
- Match existing testing frameworks, structure, and style.
- Do not add tests solely to demonstrate activity.
Uncertainty & Escalation
- Do not guess when requirements or constraints are unclear.
- Ask clarifying questions if assumptions materially affect correctness.
- Surface uncertainties, tradeoffs, or risks explicitly in explanations.
Communication Hygiene
- Explain why changes were made, not just what changed.
- Call out risks, limitations, or follow-ups when relevant.
- Be concise, factual, and neutral in tone.
Common Failure Modes
Avoid the following unless explicitly requested:
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 · 72 lines · 42 tokens per session scan A 2305e23cf0ea
general-software-engineering is a skill published in the GitHub repository CrypticSwarm/Swarmforge (2 stars, last pushed 3d ago), licensed MIT. It adds 42 tokens to every session and 461 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…