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 paultyng/skill-issue --skill match-voicegit clone --depth 1 https://github.com/paultyng/skill-issueWrote 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/paultyng/skill-issue/match-voice)<a href="https://agentmods.dev/skills/paultyng/skill-issue/match-voice"><img src="https://agentmods.dev/badge/skills/paultyng/skill-issue/match-voice.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00081 | $0.01274 |
| Opus 5 | $0.00041 | $0.00637 |
| Sonnet 5 | $0.00016 | $0.00255 |
| Haiku 4.5 | $0.00008 | $0.00127 |
Grade A, and why
match-voice 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 7d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Match Voice
Rewrite supplied text, or draft from bullets, so it reads in the user's natural voice and in keyboard-typed prose. Preserve meaning; never invent claims or facts. Normalizing typography is about reading like a human typed it on a keyboard, not about hiding that an agent wrote it (surfacing agent authorship is fine).
Output lands in Slack announcements, docs, PRs, commit bodies. It is always properly capitalized (sentence casing).
Modes
- Rewrite — text is supplied: recast it in-voice.
- Draft — only bullets/intent supplied: write it in-voice. Add no facts beyond the input.
The voice
Surface is fixed: proper capitalization (sentence casing), apostrophes intact, no emoji (allowed only when the target is Slack, and opt-in). Lowercase-everything is not the voice, it was just the casual surface. The personality below is the voice, and it carries into formal output unchanged.
- Conclusion first. State the call, then the why. ("Auto-management was paternalistic." then the reasons.)
- Blunt and dry, lightly self-deprecating. The wit is load-bearing, not decoration. Keep the bite when formalizing: "we test locally and merge on green" survives the jump from "i just yolo merge, what could go wrong" — same edge, proper casing. Do not sand it into corporate-neutral.
- Plain words, short precise verbs — wire, gate, cap, shim, sweep, surface, flesh out, lock, pull. Jargon only when needed, defined on first use.
- Label uncertainty; don't hedge it. Say "unsure", "not sure", "open question" as explicit flags. Separate what you know from what you suspect. Never a hedge pileup ("I think this might possibly").
- Parenthetical asides for the side-thought. Bullets over prose for lists. Bold the load-bearing phrase.
- Aphoristic punch where it fits: short declaratives ("This is a feature, not a bug.").
- "we" framing for shared work.
Strip the anti-voice
Cut on sight:
- Corporate filler — leverage, synergy, actionable, ensure, "in order to", "moving the needle", "data-driven * framework", robust, seamless.
- Enthusiasm openers — "Excited to announce", "This PR adds exciting".
- Hedge pileups — "I think this might possibly".
- Closing pleasantries — "Let me know if you have questions!", "Hope this helps".
- AI recap verbs — emphasized, highlighted, stressed, "The team discussed".
- Generic headers — Overview, Background, Introduction. Name the section for what it says.
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.
- 7d ago First seen · 75 lines · 81 tokens per session scan A 44995b27c84a
match-voice is a skill published in the GitHub repository paultyng/skill-issue (9 stars, last pushed 27d ago), licensed MIT. It adds 81 tokens to every session and 1,274 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
chatcrystal-debug-recall
Recall ChatCrystal memories for debugging tasks involving failing tests, compiler errors, runtime exceptions, dependency issues, environment breakage, or performance regressions. Use when historical root causes, fixes, or pitfalls may accelerate diagnosis before proposing a fix.
verify
Fact-check claims encountered during reading — dates, names, events, citations. Use when encountering historical facts or disputed claims.
megalinter-check
Collect MegaLinter lint errors for the current repository. Use when the user wants to know if the code passes linting, why the MegaLinter CI job fails, or before/after fixing lint errors. Two modes - watch a CI job (GitHub Actions, GitLab CI, Azure Pipelines, Bitbucket Pipelines) and parse its logs, or run MegaLinter…
assistant
Assistant — on any repo, scan README→docs→AGENTS→CONTRIBUTING→PR templates→task runners→devcontainer→CI→configs before code; cite sources; prefer AGENTS.md for agent behavior; portable across Cursor/Copilot/Claude; use agent-toolkit CLI when needed.
design-improvement
WHAT - Browser-grounded iterative design improvement. Consumes design-assessment findings, defines direction, prioritizes safe vs ambiguous changes, implements within existing design system, runs app, captures rendered evidence via browser, reviews and iterates. Reuses evidence model — no new scoring framework.
codeql
CodeQL operational workflow — discover/config, run/inspect, triage SARIF findings (rule/query ID, source→sink, evidence), remediate, re-validate. Distinguishes broad MegaLinter linting from semantic security analysis.