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/fledgeling-co/fledgeling-plugins/clarifynpx skills add fledgeling-co/fledgeling-plugins --skill clarifygit clone --depth 1 https://github.com/fledgeling-co/fledgeling-pluginsWrote 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/fledgeling-co/fledgeling-plugins/clarify)<a href="https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/clarify"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/clarify.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 | $0.00307 | $0.07323 |
| Opus 5 | $0.00153 | $0.03661 |
| Sonnet 5 | $0.00061 | $0.01465 |
| Haiku 4.5 | $0.00031 | $0.00732 |
Grade A, and why
clarify 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 4d 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 — 519 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clarify
Asking is expensive. It costs the user a context switch, and it costs you their confidence if the answer was somewhere you could have looked. Not asking is also expensive: work built on a guess gets thrown away, and the user finds out last.
So this is three jobs, and they fail differently:
| Job | The failure it prevents |
|---|---|
| The gate — should this be a question at all? | Interrupting for something already on disk, something that changes nothing, something you were supposed to decide, or something another model would have settled for the price of one call |
| The craft — what does the question look like? | A question that costs more to answer than to ignore |
| The handling — what happens to the answer? | Reading the option label and discarding the note attached to it |
Most agents fail the gate, then fail the craft, then never notice they failed the handling.
Running as a Gemini model? Read gemini.md in this directory first, then follow this file with the overrides it names. It gives gate 1's sweep, the referral and the panel a count each, requires every lane verdict to be quoted from the lane's output file, and turns the Shape table's caps into a bound ledger read back off the payload. Other models skip it.
The gate
Five steps, run in order. The first one that resolves ends it, and by construction most forks never reach the last two.
1. Is it already answered?
Sweep before you compose anything. The answer usually exists:
- This conversation — including what the user mentioned in passing, three messages ago, while talking about something else. This is the most common place the answer already is.
- The repo —
CLAUDE.md,README, config files, the manifest, existing code that already made this decision once. - Work already done this session — a subagent's findings, a plan file, a failed run's partial output, a research report, tool output you have not re-read. Long sessions are where answers get lost, and re-asking is how the user finds out you lost one.
- The files themselves — open them. A question about code you have not read is not a clarifying question, it is a substitute for reading.
What ships with it
4 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.
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.
- 4d ago First seen · 519 lines · 307 tokens per session scan A 8e041ecffb1f
clarify is a skill published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed yesterday), licensed MIT. It adds 307 tokens to every session and 7,323 once invoked, about $0.0015 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.
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
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…
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…