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/n-n-code/n-n-code-skills/coding-guidance-cppnpx skills add n-n-code/n-n-code-skills --skill coding-guidance-cppgit clone --depth 1 https://github.com/n-n-code/n-n-code-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 | $0.00072 | $0.02242 |
| Opus 5 | $0.00036 | $0.01121 |
| Sonnet 5 | $0.00014 | $0.00448 |
| Haiku 4.5 | $0.00007 | $0.00224 |
Grade A, and why
coding-guidance-cpp 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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
C++ Coding Guidance
This skill adds portable C++ implementation, refactoring, and review guidance.
Adjacent Skills
This skill provides portable C++ engineering principles. Compose with:
- Workflow: thinking (ambiguous decision framing), recursive-thinking (stress-testing), security (threat modeling)
- Domain overlays: backend-guidance (server-side code), backend-systems-guidance (stronger backend architecture, reliability, and trust-boundary work), ui-guidance (graphical UI/web frontend), project-core-dev (repo-specific completion discovery and reporting when needed)
- Qt specialization: coding-guidance-qt when Qt object lifetime, eventing, widgets, models, thread affinity, or generated build steps dominate
When Not to Lean on This Skill
- non-C++ work
- legacy or bare-metal environments where modern C++ guidance must be adapted selectively
- pure architecture or process work with no C++ design or code judgment needed
- repo-specific style packs or platform policies that should be enforced by
local
clang-tidy, compiler, or overlay rules rather than a portable principle skill
Boundary Contract
Keep this skill focused on portable C++ engineering judgment.
- Put repo-specific exception policy, warning policy, formatter choices, and include-order rules in repo config or repo docs
- Put style-pack rules from ecosystems such as Google, LLVM, Abseil, or platform/vendor bundles in repo config or overlays, not here
- Put library- or platform-specific API policy in repo config or a domain overlay
- When a rule is analyzer-shaped but not portable, keep it in
clang-tidyconfig or the reference note rather than adding it to the main skill
Implementation Workflow
- Read the touched code, build shape, existing tests, and any nearby docs or shorthand notes before editing.
- If the request is partially specified, infer the intended behavior from the existing code and tests. Ask only when multiple plausible C++ designs would change semantics.
- Choose the narrowest change that solves the problem without hiding ownership, lifetime, or error-handling contracts.
- Implement with simple, strongly typed interfaces and modern C++ defaults.
- Add or update tests close to the changed behavior.
- Run the narrowest relevant format, build, test, sanitizer, and analyzer targets the repo supports.
What ships with it
3 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 · 216 lines · 72 tokens per session scan A 60d9a7c5c043
coding-guidance-cpp is a skill published in the GitHub repository n-n-code/n-n-code-skills (4 stars, last pushed 4d ago), licensed MIT. It adds 72 tokens to every session and 2,242 once invoked, about $0.0004 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
cocoscout
Relevance-ranked context loading — Tier 2 async subagent (Haiku, <5s) that fires after Tier 1 deterministic checks in UserPromptSubmit. Injects ranked context from CocoGrove, CocoContext, Environment Inspector, Prompt Studio, and CocoDream.
cocowatch
Developer engagement observer — non-blocking, always-on observational layer that tracks Delegation Intensity, Review Depth, and Engagement Zone throughout a session. Summary surfaced at $ship and FULL checkpoints.
the-grilling
Use when adversarial brainstorming is needed after reconnaissance — the Proposer, Devils-Advocate, and Synthesizer each run ONE pass (no rounds); the Don is grilled on the IDEA first, one question at a time, then the proposal is attacked.
using-gangsta
Use when starting any conversation — establishes how to find and use Gangsta skills, enforces the 1% invocation rule, maps platform tools, and routes the Don's intent through the Gangsta Agents Family hierarchy.
interrogation-debugging
Use when encountering any bug, test failure, or unexpected behavior — finds the rat in the code through systematic root-cause interrogation before any fix attempts.
the-hit
Use when the execution plan is approved and it is time for parallel execution — dispatches workers through crew leads to implement work packages with TDD enforcement, report collection, and escalation protocols.