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/moasq/agentic-ship/plain-languagenpx skills add moasq/agentic-ship --skill plain-languagegit clone --depth 1 https://github.com/moasq/agentic-shipWhat 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 | $0.00035 | $0.02057 |
| Opus 5 | $0.00017 | $0.01028 |
| Sonnet 5 | $0.00007 | $0.00411 |
| Haiku 4.5 | $0.00003 | $0.00206 |
Grade A, and why
plain-language 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 3d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit project prose against the pl-01..pl-33 rule catalog and produce one findings document with verified rewrites. This skill is read-only over the reviewed files: it recommends, it never edits. The state file is for your own resumability, not human review.
Mirror the four phases below in the host's todo tool so the user sees progress.
Non-negotiables (read first)
- Never modify reviewed files. Findings and rewrites go in the plan document only.
- Explicit invocation only. This skill runs when the user invokes
/plain-language— never auto-activate. - Classify every finding FALSIFIABLE (cites exact prose on a specific line that Grep can confirm) or OPINION (tone, audience fit, ambiguity — interpretation-dependent).
- Grep-verify every FALSIFIABLE citation against the cited file before it enters the draft. No match → drop the finding and count it as a dropped hallucination.
- One output file. The consolidated plan is the single user-facing artifact; your end-of-run reply names only its path, never the state file or intermediate details.
Scope
- Review: prose in
.md,.mdx,.markdown,.txt,.rst,.adoc,.org,.wikifiles; UI strings; error messages. - Skip: code inside fences and backticks, variable names, import statements, configuration values, URLs, file paths.
- Preserve technical terms: flag jargon only when a simpler alternative exists without losing precision.
- Exclude: dotdirs,
node_modules/,vendor/,dist/,build/,coverage/,__pycache__/,target/,venv/, anything in.gitignore. - Never scan the skill's own directory. Always work from the user's project root. A bare
/plain-languagereviews all in-scope prose from the project root; ask only when the project root is ambiguous or the user named files that don't exist. - Plain language checks readability, not doc/code accuracy — doc/code drift detection is out of scope.
State file
Working state lives at .agent-state/plain-language/plain-language-YYYY-MM-DD.md (today's date; house path — upstream uses .agents/local/state/, but in this repository .agent-state/ is the one gitignored home for runtime state). Never shown to the user, never committed.
What ships with it
8 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.
- LICENSE 1.0 KB
- references/active-voice-guide.md 2.1 KB
- references/adversarial-review-prompt.md 3.1 KB
- references/before-and-after-examples.md 7.8 KB
- references/final-plan-format.md 2.5 KB
- references/rules-quick-ref.md 5.5 KB
- references/severity-rubric.md 2.8 KB
- references/word-substitutions.md 5.6 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.
- 3d ago First seen · 114 lines · 35 tokens per session scan A 527bfa735c27
plain-language is a skill published in the GitHub repository moasq/agentic-ship (10 stars, last pushed 4d ago), licensed MIT. It adds 35 tokens to every session and 2,057 once invoked, about $0.0002 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…