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 mhmdreza-rafiei/agent-tools --skill estimategit clone --depth 1 https://github.com/mhmdreza-rafiei/agent-toolsWrote 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/mhmdreza-rafiei/agent-tools/estimate)<a href="https://agentmods.dev/skills/mhmdreza-rafiei/agent-tools/estimate"><img src="https://agentmods.dev/badge/skills/mhmdreza-rafiei/agent-tools/estimate/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/mhmdreza-rafiei/agent-tools/estimate"><img src="https://agentmods.dev/badge/skills/mhmdreza-rafiei/agent-tools/estimate.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00075 | $0.00681 |
| Opus 5 | $0.00037 | $0.00341 |
| Sonnet 5 | $0.00015 | $0.00136 |
| Haiku 4.5 | $0.00007 | $0.00068 |
Grade A, and why
estimate 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 8d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/estimate
Size the work before commitment, not after. A bad estimate is usually a missing scope or a hidden risk, not bad math. Estimate surfaces both.
When to use
Before committing to a feature; when the user says "how big is this?" or
"estimate"; on /estimate; pairs with /spec once a spec exists.
Commands
/estimate— estimate the current task from context./estimate <feature>— estimate a named feature./estimate --split— also propose where to split if the size is L or above.
Step 1 — Read the spec / context
- If
context/plan.mdor a spec exists, read it. If not, ask the user for the goal and scope (max 3 questions). - Scan the code the task touches (imports, callers, tests) to ground the estimate in reality, not optimism.
Step 2 — Size
Produce:
- Size —
S/M/L/XL, with a one-line definition of each band (e.g. S = < 1 session, M = 1–2 sessions, L = 3–5, XL = split required). - Hours — a range, not a point (e.g. 4–8h). State assumptions.
- Riskiest parts — 1–3 items, each with why it's risky.
- Split candidates — if L or XL, name 2–3 sub-tasks that could ship independently.
Step 3 — Flag what would blow the estimate
- Hidden scope (touches X, Y, Z systems).
- Missing specs / unclear acceptance criteria.
- Destructive ops (migrations, deletions) that need a checkpoint.
- External dependencies (vendor, another team).
Output
## Estimate
- Size: M (1–2 sessions)
- Hours: 4–8h
- Riskiest: <part> — <why>
- Split candidates: <sub-task A>, <sub-task B>
## What could blow this
- <risk>
Constraints
- Range, never a point estimate. State assumptions.
- Ground in the actual code, not optimism.
- Do not invent scope; if unclear, ask (max 3) or mark as a risk.
Related artifacts
/workflow/spec(load first) — provides the scope to estimate against./context/architect— plans the build this estimates.rule/global/ask-dont-guess— ask when scope is unclear.
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.
- 8d ago First seen · 77 lines · 75 tokens per session scan A 1b91a5ac221b
estimate is a skill published in the GitHub repository mhmdreza-rafiei/agent-tools (5 stars, last pushed 24d ago), licensed MIT. It adds 75 tokens to every session and 681 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 2026-09-03.
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…