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 instructions/srnichols/plan-forge/clean-codegit clone --depth 1 https://github.com/srnichols/plan-forgeWhat 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 | $0.01500 | $0.01500 |
| Opus 5 | $0.00750 | $0.00750 |
| Sonnet 5 | $0.00300 | $0.00300 |
| Haiku 4.5 | $0.00150 | $0.00150 |
Grade A, and why
plan-forge clean-code.instructions.md 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 yesterday.
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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clean Code Guardrails
Derived from the Phase 42 Clean-Code Audit (27 findings, 6 categories). Full catalog:
docs/plans/cleanup-findings/CATALOG.md
When writing a function
| Rule | Threshold | Action |
|---|---|---|
| Length | ≤100 lines (warn) / ≤300 lines (error) | Extract helpers; split by single responsibility |
| Complexity | ≤12 paths (warn) / ≤20 paths (error) | Flatten conditionals; extract guard clauses |
| Parameters | ≤4 positional (warn) / ≤6 (error) | Wrap excess args in an options object |
| Nesting depth | ≤3 levels | Invert conditions; extract inner blocks |
Checks before merging a function change:
- Function does exactly one thing (name is a verb phrase, single concern)
- No positional parameter list longer than 4 — use
{ a, b, c }destructuring - No magic numbers — assign to a named
constat module scope - No side effects beyond the function's stated contract
- ESLint
complexity-errorandmax-lines-per-function-errormust be zero
When naming
- Modules / files: noun, kebab-case (
cost-service.mjs, notcs.mjs) - Functions: verb phrase, reveals intent (
buildEstimate, notcalc) - Variables: noun, camelCase; boolean prefixed
is/has/can - Constants: UPPER_SNAKE for true compile-time literals; camelCase
constfor runtime values - Enums / frozen arrays: import from
pforge-mcp/enums.mjs— never hand-type string literals - Avoid:
data,info,result,tmp,val, single letters outside loop indices
When commenting
- Comment why, not what — the code shows what; the comment explains why it had to be this way
- Delete commented-out code; use
gitfor history - JSDoc only on exported API surfaces; inline comments are a last resort
- Do NOT leave
TODO/FIXME/HACKmarkers — create a tracked issue instead console.logmust be intentional CLI output; remove debug leakage before committing
When you spot duplication (DRY)
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.
- yesterday First seen · 129 lines · 1,500 tokens per session scan A 99308c389ea9
plan-forge clean-code.instructions.md is an instructions file published in the GitHub repository srnichols/plan-forge (5 stars, last pushed 21d ago), licensed MIT. It adds 1,500 tokens to every session, about $0.0075 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 instructions, from other repositories
dotnet-skills AGENTS.md
Instructions for managedcode/dotnet-skills, covering agents.md, purpose, solution topology, rule precedence and path and linking rules.
dotnet-skills copilot-instructions.md
Instructions for managedcode/dotnet-skills: Use AGENTS.md as the repository-wide source of truth for workflow, catalog structure, release policy, and skill maintenance rules.
Perigon.CLI copilot-instructions.md
Instructions for AterDev/Perigon.CLI, covering github copilot instructions, general guidelines, 技术栈, 项目结构与分层 and 代码风格约定.
copilot-instructions copilot-instructions.md
Instructions for SebastienDegodez/copilot-instructions, covering copilot instructions, language policy, development code generation and workflow implementation.
maf-doctor maf-deployment.instructions.md
Always-loaded production-deployment patterns for MAF 1.3.0. Auto-applies to Program.cs, DI registration files, and infra config. Covers ManagedIdentityCredential, MaxTokens caps, secret handling, OpenTelemetry wiring, and the analyzer rules that catch regressions at write time.
maf-doctor copilot-instructions.md
Instructions for joslat/maf-doctor, covering maf 1.3.0 migration — auto-loaded constraints, maf 1.3.0 — constraints & breaking changes reference, hard constraints (never violate), fan-out / fan-in rules (silent failure risk) and key breaking changes.