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/dhananjay625/dev-workflow/code-minimalismnpx skills add Dhananjay625/dev-workflow --skill code-minimalismgit clone --depth 1 https://github.com/Dhananjay625/dev-workflowWhat 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 | $0.00068 | $0.00816 |
| Opus 5 | $0.00034 | $0.00408 |
| Sonnet 5 | $0.00014 | $0.00163 |
| Haiku 4.5 | $0.00007 | $0.00082 |
Grade A, and why
code-minimalism 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code minimalism
Core principle: every line is a liability. Write only what the spec demands. When requirements change, add then — never predict.
Step 1 — Set the context tier FIRST
Minimalism is calibrated, not absolute. Before writing, classify:
| Tier | Examples | Baseline that is NOT bloat |
|---|---|---|
| T1 Throwaway | one-off script, exploration, spike | Nothing. Tracebacks are the error handling. |
| T2 Tool | CLI/script others will run repeatedly | Handle bad input paths + malformed input; usage line on wrong args. |
| T3 Production | service, API, pipeline, library | Input validation on all external input; error handling for network/file/timeout; logging on errors and state changes; nulls/duplicates/empty handled in data-touching code; type hints on public interfaces. |
The tier baseline is part of the spec even when unwritten. Everything ABOVE the tier baseline needs explicit spec justification. Everything below it is negligence, not minimalism.
Step 2 — Write only what passes these gates
Before each addition, one of these must be true, else delete:
- The spec explicitly requires it.
- The tier baseline (table above) requires it.
- Its absence causes a failure that WILL occur in normal use.
Never write: features "for later", scaling beyond stated load, abstraction layers for imagined reuse, config keys for values that never change, comments restating the code, docstrings on obvious functions, tests for code that cannot fail.
Step 3 — Structure rules
- Inline until 3 uses: no helper, class, or util for a single call site.
- No class where a function works; no function where an expression works.
- Stdlib first: add a dependency only if it replaces >~30 lines of nontrivial code you'd otherwise maintain, or provides correctness you can't easily get (crypto, timezone math, parsing standards).
- Flat until it hurts: no folder with 1–2 files; no layer directories (controllers/services/models) for a handful of endpoints.
- Comment WHY (chosen approach, workaround, assumption), never WHAT.
- Split only on real pressure: function doing 3+ distinct things, file >~500 lines, 4+ branch conditionals.
What ships with it
1 file 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.
- yesterday First seen · 78 lines · 68 tokens per session scan A 0682d36c4094
code-minimalism is a skill published in the GitHub repository Dhananjay625/dev-workflow (2 stars, last pushed 20d ago), licensed MIT. It adds 68 tokens to every session and 816 once invoked, about $0.0003 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.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…