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 gohypergiant/agent-skills --skill accelint-skill-prosegit clone --depth 1 https://github.com/gohypergiant/agent-skillsWrote 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/gohypergiant/agent-skills/accelint-skill-prose)<a href="https://agentmods.dev/skills/gohypergiant/agent-skills/accelint-skill-prose"><img src="https://agentmods.dev/badge/skills/gohypergiant/agent-skills/accelint-skill-prose/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/gohypergiant/agent-skills/accelint-skill-prose"><img src="https://agentmods.dev/badge/skills/gohypergiant/agent-skills/accelint-skill-prose.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high System Prompt Leakage · line 467 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
- medium Excessive Agency · line 162 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- low Excessive Agency · line 47 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
- low Excessive Agency · line 188 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 | $0.00140 | $0.04116 |
| Opus 5 | $0.00070 | $0.02058 |
| Sonnet 5 | $0.00028 | $0.00823 |
| Haiku 4.5 | $0.00014 | $0.00412 |
Grade A, and why
accelint-skill-prose 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 — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Prose
Use this skill to audit or revise behavior-defining prose while preserving behavior by default.
Scope and core contract
Use this skill for SKILL.md, AGENTS.md, CLAUDE.md, behavior-bearing references, prompt templates, workflow guidance, guardrails, and other prose whose wording controls trigger coverage, workflow order, approval semantics, guardrail strength, or exact technical meaning.
Do not use it for broader content strategy, policy design, domain review, ordinary low-risk prose cleanup, or agent-skill description optimization managed by another skill.
Preserve, in this priority order:
- trigger intent and scope;
- workflow semantics and approval logic;
- guardrail and hard-stop strength;
- exact technical meaning; then
- clarity and brevity.
Treat behavior-bearing prose as an execution contract, not as ordinary style copy. Keep one term for one concept when the source treats the terms as equivalent. Do not rotate synonyms for style.
Hard stops
- Never broaden or narrow trigger coverage silently.
- Never weaken a hard requirement into advice or elevate optional guidance into a hard requirement.
- Never reorder behavior-bearing workflow steps, branches, gates, or approval timing without explicit approval.
- Never paraphrase exact paths, commands, flags, fields, identifiers, inline code, code blocks, quoted text, or scope-defining examples without explicit approval.
- Never turn a warning, rationale, note, or descriptive statement into a new gate, prerequisite, branch, or policy without source evidence.
- Never use a qualitative term as a substitute for an operational condition when it acts as a hidden gate, fallback, exception, or permission slip.
- Never treat numbering, headings, checklists, XML, or another presentation convention as a workflow control unless the source or active harness makes it behavior-bearing.
- Never claim that a rubric grade is a validated measurement, that a finding proves runtime behavior, or that a format preference is a validated compliance improvement without local evidence.
- Never treat an isolated reviewer’s output as verified evidence or average, vote on, or otherwise aggregate local grades.
- Never hide an unavailable required reviewer or present incomplete rubric coverage as complete.
- Never begin work that depends on an unresolved user decision or required approval.
- Never skip auditing, grading, recommendations, rewrite-proposal synthesis, or rewriting because report visibility is suppressed.
What ships with it
10 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.
- assets/output-template.md 5.3 KB
- CHANGELOG.md 28 KB
- evals/evals.json 60 KB
- README.md 6.0 KB
- references/normative-language.md 5.4 KB
- references/serial-instruction-guidance.md 14 KB
- references/ste-compatible-rules.md 5.1 KB
- references/user-question-waiting.md 16 KB
- research/interactive-decisions.md 32 KB
- research/serial-instructions.md 36 KB
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 Changed · -410 lines · -6 tokens per session 89e9a7e77e5a
- 12d ago First seen · 648 lines · 146 tokens per session scan A e37de0d944f5
accelint-skill-prose is a skill published in the GitHub repository gohypergiant/agent-skills (24 stars, last pushed today), licensed Apache-2.0. It adds 140 tokens to every session and 4,116 once invoked, about $0.0007 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…