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 skills add xcrft/mastermind --skill no-ai-slop-commentsgit clone --depth 1 https://github.com/xcrft/mastermindWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/xcrft/mastermind/no-ai-slop-comments)<a href="https://agentmods.dev/skills/xcrft/mastermind/no-ai-slop-comments"><img src="https://agentmods.dev/badge/skills/xcrft/mastermind/no-ai-slop-comments/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/xcrft/mastermind/no-ai-slop-comments"><img src="https://agentmods.dev/badge/skills/xcrft/mastermind/no-ai-slop-comments.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What 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 5.1 | $0.00085 | $0.01152 |
| Opus 5 | $0.00043 | $0.00576 |
| Sonnet 5 | $0.00017 | $0.00230 |
| Haiku 4.5 | $0.00009 | $0.00115 |
Grade A, and why
no-ai-slop-comments 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 9d 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.
No AI-Slop Comments
LLMs over-comment. Left unchecked, they narrate every line, banner every section, and annotate every edit. Apply this rule to comments added or modified in the current change. Do not turn a scoped implementation into a repository-wide comment cleanup.
When to use
- Writing new code, or editing existing code, in any language.
- Implementing a spec as an executor — preserve literal blocks and add comments only when the contract or code needs information the code cannot express.
- Reviewing a diff that reads like a tutorial:
// loop over users,# increment counter,// --- Helpers ---. - The user says "stop commenting", "no slop comments", or "you comment too much".
The rule
A comment must say something the code cannot. If a comment you added or changed loses no information when deleted, remove it.
Comments explain why, not what. The code already says what it does.
Default to zero new comments. A generated function does not need a heading, step labels, or a sentence above each branch merely because it is new.
Delete these — slop
| Category | Slop example | Why it's slop |
|---|---|---|
| Restating code | i += 1 // increment i |
The code already says it. |
| Narrating intent | // loop over users above for u in users: |
The loop says it. |
| Section banners | // ===== Helpers =====, # --- main --- |
Structure isn't prose. Use functions. |
| Step narration | // Step 1: validate, // First, we… |
You're talking to yourself. |
| Edit markers | // added, // changed per request, // NEW |
Git is the changelog, not the source. |
| Echoing the signature | a docstring that re-says the function name as a sentence | More words, no information. |
| Dead code | // const old = ... left behind |
Delete it; git remembers. |
| Ownerless TODO | // TODO: fix later |
No owner, no ticket, no action. |
Keep these — they earn their place
- Why, not what:
// Retry 3×: the upstream API 503s under burst load (INFRA-1421). - Non-obvious workaround:
// Round before compare — float drift makes == flaky here. - Invariant a caller must respect:
// Caller must hold the mutex before calling. - Deliberate, surprising choice:
// O(n²) is fine — n ≤ 8 by schema constraint. - Dense-logic intent: one line over a gnarly regex / bit-twiddle saying what it matches.
- Required ceremony: public-API docstrings where the project convention demands them; license headers.
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.
- 9d ago First seen · 112 lines · 85 tokens per session scan A a0ae2fca7a2f
no-ai-slop-comments is a skill published in the GitHub repository xcrft/mastermind (11 stars, last pushed today), licensed MIT. It adds 85 tokens to every session and 1,152 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 2026-08-30.
Other skills, from other repositories
projectatlas
Use ProjectAtlas as the atlas-first orientation layer before broad source reads, with MCP-first task startup, short-alias worktree registration and routing, safe targeted initialization, ranked navigation, exact or federated graph evidence, purpose curation, health, lint, and repository-wide token reporting.
truecourse-hooks
Install, configure, or remove the TrueCourse pre-commit hook.
codex-coding-plugin
Build, review, or fix ProjectAtlas plugin/runtime installer integration for Codex, Claude Code, and OpenCode, especially version convergence, stale ProjectAtlas cache repair, MCP config generation, skill artifacts, host smoke tests, and fake-host tests for ProjectAtlas releases.
repo-harness
Route explicit repo-harness setup, planning, execution, verification, and handoff actions through deterministic repository state.
cymbal
Tree-sitter indexed code navigator. Use the cymbal CLI — not Read, Grep, Glob, or Bash — for finding where symbols are defined, tracing callers and callees, locating interface implementations, understanding the impact of a change, and mapping imports across an existing codebase. Returns precise, token-efficient…
obsidian-memory
Cross-project long-term memory over an Obsidian brain vault: recall relevant notes before a task, and persist distilled conclusions (decisions, pitfalls, solutions, progress) back after a task. The vault is an optional aggregation/projection layer — repo-local artifacts stay the per-project source of truth, and sync…