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 xD4O/praxis --skill estimationgit clone --depth 1 https://github.com/xD4O/praxisWrote 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/xd4o/praxis/estimation)<a href="https://agentmods.dev/skills/xd4o/praxis/estimation"><img src="https://agentmods.dev/badge/skills/xd4o/praxis/estimation/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/xd4o/praxis/estimation"><img src="https://agentmods.dev/badge/skills/xd4o/praxis/estimation.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 | $0.00081 | $0.01244 |
| Opus 5.5 | $0.00032 | $0.00498 |
| Sonnet 5.5 | $0.00016 | $0.00249 |
| Haiku 4.5 | $0.00008 | $0.00124 |
Grade A, and why
estimation 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 15d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Estimation Protocol
EXTREMELY_IMPORTANT: This is a MANDATORY protocol, not a suggestion. Follow every step. Do not skip steps. Do not combine steps. Do not summarize. Work through each gate in order.
You are about to attach a number to future work. Unexamined estimates are optimism with a unit. Follow this protocol before any number reaches the user.
STEP 1 — Decompose until estimable
Break the work into pieces. Apply the test to EACH piece: "Can I state a bounded estimate for this piece and say why?" If you cannot, it is not broken down enough — split it again. Repeat until every leaf piece passes.
A piece that resists decomposition ("integrate with their API... somehow") is not an estimation problem, it is an unknown. Move it to STEP 3's unknowns list and, if it dominates the total, recommend a timeboxed spike BEFORE estimating the rest.
STEP 2 — Reference-class forecast each piece
For each piece, ask in order: Has this agent done comparable work this session? In this codebase? Is there a well-known reference class (e.g., "CRUD endpoint", "schema migration", "OAuth integration")?
- If YES → anchor on what that comparable work ACTUALLY took, not what it should have taken. Mark the piece REF-BACKED.
- If NO → estimate from structure, then mark the piece GUESSED and double its range width. Do not silently treat a guess like a reference.
Tally the counts: N pieces REF-BACKED, M pieces GUESSED. You will need this in STEP 5.
STEP 3 — Produce a range, never a point
For the total, state LOW and HIGH bounds, not one number. Then name the SPECIFIC unknowns that widen the range — each unknown must be a noun you could investigate ("their API's rate-limit behavior"), not a vibe ("some risk").
If asked for a single number anyway, give the range and say which bound you would commit to and why. Never collapse the range silently.
STEP 4 — Planning-fallacy check
Ask explicitly: "What is usually forgotten in estimates like this?" Check each:
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.
- 15d ago First seen · 111 lines · 81 tokens per session scan A 5fc3dc3a18b5
estimation is a skill published in the GitHub repository xD4O/praxis (28 stars, last pushed 2mo ago), licensed MIT. It adds 81 tokens to every session and 1,244 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-02.
Other skills, from other repositories
story-readiness
Is a story implementation-ready? Checks clear acceptance criteria, open questions, ADR refs. READY/NEEDS WORK/BLOCKED/NOT ASSESSED.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
remove
Remove a deployed framework or addon from the current workspace.