Microsoft Discovery is an extensible platform for scientific research and research-and-development workflows that combines agent orchestration, reasoning, graph-based knowledge, and high-performance computing. Researchers, partners, and product users use its Azure enterprise platform or local Windows app to explore and build research workflows. The catalogue entries provide skills and instructions for working with the Discovery community and platform.
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 microsoft/discovery --skill token-estimator-mvpgit clone --depth 1 https://github.com/microsoft/discoveryWrote 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/microsoft/discovery/token-estimator-mvp)<a href="https://agentmods.dev/skills/microsoft/discovery/token-estimator-mvp"><img src="https://agentmods.dev/badge/skills/microsoft/discovery/token-estimator-mvp/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/microsoft/discovery/token-estimator-mvp"><img src="https://agentmods.dev/badge/skills/microsoft/discovery/token-estimator-mvp.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 | $0.00034 | $0.00397 |
| Opus 5.5 | $0.00014 | $0.00159 |
| Sonnet 5.5 | $0.00007 | $0.00079 |
| Haiku 4.5 | $0.00003 | $0.00040 |
Grade A, and why
token-estimator-mvp 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 2d 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.
What it actually says
Token estimator MVP
Use this skill for first-pass AI planning guidance. It is not a scientific execution service.
Use only the bundled CLI or API with calibration and profiles. Never invent formulas or ask users for token budgets.
Procedure
-
Identify the deliverable from the request. Context is optional.
-
Map to the input guide and contract, version 1.2.0.
-
Leave unknown facts unknown. Provide conditional bases when supported.
-
For "run an existing workflow," use
existing-workflow-operation. -
Count shared setup/checks once. Separate independent review as its own task.
-
Run the estimator with sanitized JSON:
node scripts/estimate.js --input examples/coarse-prediction.json -
Report status, mapping, assumptions, uncertainty and exclusions.
Package notes
Copy this entire directory to skills/token-estimator-mvp/ in the target
repository. Keep files relative and project-local. No installs, credentials,
network access, or external authoring workspace are required.
See examples for supported scenarios.
Run tests:
node --test tests/model.test.js tests/phases.test.js tests/operations.test.js tests/behavior.test.js tests/packaging.test.js tests/skill-guidance.test.js
This package ships provisional community reference ranges. They are planning heuristics requiring broader community validation and are not statistical bounds or evidence of customer outcomes.
What ships with it
46 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.
- examples/ambiguous-prediction.json 305 B
- examples/coarse-prediction.json 140 B
- examples/computational-context.json 508 B
- examples/context.json 416 B
- examples/context/computational.md 1.9 KB
- examples/context/operation.md 1.4 KB
- examples/context/README.md 632 B
- examples/context/scientific-pipeline.sh 35 B runs code
- examples/description.json 427 B
- examples/disjoint-tasks.json 770 B
- examples/integration.json 286 B
- examples/missing-context.json 288 B
- examples/operation-bounded-monitoring.json 354 B
- examples/operation-context.json 442 B
- examples/operation-failed-setup.json 356 B
- examples/operation-ongoing.json 272 B
- examples/operation-review.json 639 B
- examples/operation-shared-checks.json 255 B
- examples/operation-unresolved.json 257 B
- examples/operation.json 307 B
- examples/partial.json 522 B
- examples/prototype.json 244 B
- examples/README.md 761 B
- examples/real-data.json 274 B
- examples/simulation.json 262 B
- examples/unsupported.json 299 B
- package.json 386 B
- README.md 755 B
- references/context-policy.md 3.9 KB
- references/input-guide.md 2.9 KB
- references/operational-evidence.md 1.0 KB
- resources/calibration.json 7.6 KB
- resources/contract.schema.json 13 KB
- resources/work-profiles.json 27 KB
- scripts/estimate.js 1.0 KB runs code
- scripts/model.js 37 KB runs code
- tests/accepted-hashes.json 863 B
- tests/behavior.test.js 2.5 KB runs code
- tests/model.test.js 3.4 KB runs code
- tests/operations.test.js 2.8 KB runs code
- tests/packaging.test.js 2.3 KB runs code
- tests/phases.test.js 3.2 KB runs code
- tests/portable-guard.cjs 2.3 KB runs code
- tests/privacy-guard.cjs 2.1 KB runs code
- tests/runtime-read-guard.cjs 543 B runs code
- tests/skill-guidance.test.js 987 B runs code
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.
- 2d ago First seen · 49 lines · 34 tokens per session scan A cfbdede38b29
token-estimator-mvp is a skill published in the GitHub repository microsoft/discovery (286 stars, last pushed 2d ago), licensed MIT. It adds 34 tokens to every session and 397 once invoked, about $0.0001 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 2026-11-06.
token-estimator-mvp compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| token-estimator-mvpmicrosoft/discovery | Skill | 286 | 2d ago | MIT | A | 34 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |