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.
git clone --depth 1 https://github.com/ngtiendong/Academic-Research-Agent-SkillWrote 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/commands/ngtiendong/academic-research-agent-skill/math-formalize)<a href="https://agentmods.dev/commands/ngtiendong/academic-research-agent-skill/math-formalize"><img src="https://agentmods.dev/badge/commands/ngtiendong/academic-research-agent-skill/math-formalize/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/commands/ngtiendong/academic-research-agent-skill/math-formalize"><img src="https://agentmods.dev/badge/commands/ngtiendong/academic-research-agent-skill/math-formalize.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 | $0.00000 | $0.00424 |
| Opus 5.5 | $0.00000 | $0.00170 |
| Sonnet 5.5 | $0.00000 | $0.00085 |
| Haiku 4.5 | $0.00000 | $0.00042 |
Grade A, and why
math-formalize 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 1mo 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/math-formalize
Act as the Strategist for mathematical formalization.
Language
Follow config/language.yaml when present.
Task
Formalize each proposed contribution before implementation.
Procedure
- Define objects, variables, inputs, outputs, constraints, and assumptions.
- State the objective or optimization target.
- Map each term to implementation interfaces where possible.
- Identify missing definitions or ambiguous notation.
- Run the metric hygiene checklist on every metric and headline claim.
- Keep the formalization as simple as the research permits.
Metric Hygiene Checklist
Apply before any metric enters a draft or experiment code:
- Notation completeness: every symbol in every formula has a formal definition, including "obvious" ones (state any conditioning and the targeted/untargeted variant).
- Null model validity: interaction or composition metrics on bounded
[0,1]variables use an independence null1-(1-p_j)(1-p_k)or a log-odds scale, never an additive nullp_j + p_k. - Ratio safety: any ratio metric proves its denominator is bounded away from zero, or is replaced by an absolute residual with a bootstrap confidence interval.
- Operational definitions: every quantitative headline term (e.g. "sub-threshold", "phase transition", "emergent") has a numeric threshold and a measurement procedure.
- Claim-arm coverage: each claim gate names the specific experiment arm or ID that feeds it; a gate without an arm is a critical defect.
- Computability: any metric without a concrete measurement procedure is flagged exploratory, not headline.
- Capability and treatment validity: a disruption claim names the untreated capability check, matched control, and procedure proving the treatment survives preprocessing without changing the task truth.
Output
NotationProblem DefinitionObjectiveAssumptionsConstraintsImplementation MappingAmbiguitiesMetric Hygiene Result: pass or list of failing itemsMath Readiness Scorefrom 1 to 9
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.
- 1mo ago Changed · +1 lines e259e334c480
- 2mo ago First seen · 44 lines · 0 tokens per session scan A 91023f8169a9
math-formalize is a command published in the GitHub repository ngtiendong/Academic-Research-Agent-Skill (68 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 424 tokens. 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 2026-08-30.
math-formalize compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| math-formalizengtiendong/Academic-Research-Agent-Skill | Command | 68 | 1mo ago | MIT | A | 0 | Claude Code |
| checklistgithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| clarifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 27 | Claude Code |
| specifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| analyzegithub/spec-kit | Command | 148k | yesterday | MIT | A | 26 | Claude Code |
| convergegithub/spec-kit | Command | 148k | yesterday | MIT | A | 35 | Claude Code |
| implementgithub/spec-kit | Command | 148k | yesterday | MIT | A | 14 | Claude Code |