Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/sweetcornna/mathodologynpx agentmods add skills/sweetcornna/mathodology/mathodology-dev-test-releaseWrote 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/sweetcornna/mathodology/mathodology-dev-test-release)<a href="https://agentmods.dev/skills/sweetcornna/mathodology/mathodology-dev-test-release"><img src="https://agentmods.dev/badge/skills/sweetcornna/mathodology/mathodology-dev-test-release.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 5.1 | $0.00036 | $0.01028 |
| Opus 5 | $0.00018 | $0.00514 |
| Sonnet 5 | $0.00007 | $0.00206 |
| Haiku 4.5 | $0.00004 | $0.00103 |
Grade A, and why
mathodology-dev-test-release 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 7d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mathodology Dev Test Release Archive
Scope
This branch is skills-only. Its active validation checks are skill, metadata, link, backup, and tracked-file whitelist checks.
The former application build, CI, Docker, native service, packaging, installer, and release files are not present on this branch. Treat those workflows as archived knowledge unless recovered from Git history.
Active Workflow Validation
For award-level modeling workflows, this skill owns final gates rather than application builds:
- phase log exists and covers Phases 0-8
- every prompt requirement maps to a paper section or package file
- every reported number maps to code, data, derivation, or documented manual calculation
- every phase has specialist handoffs, lead synthesis, and an independent critic gate
- all blocker and high-severity critic findings are fixed before final packaging
- model selection considers at least three routes with rejection reasons for alternatives
- sensitivity or robustness evidence exists for important assumptions and key results
- final paper, editable source if required, code, data notes, figures, tables, README, AI-use statement, and checklist are present
- no local caches, secrets, raw scratch files, or unrelated artifacts are in the final package
Codex should run these gates with a dedicated critic or packaging agent.
Claude Code should run mathodology-submission-packager and then mathodology-critic.
Active Validation
Shared repository validation lives in ONE place: scripts/validate_repo.py
(pure standard library, no PyYAML). Do not re-inline these checks as heredocs in
docs or other skills; add or change a gate in the script.
Run every maintenance gate from the repository root:
python3 .claude/skills/mathodology-dev-test-release/scripts/validate_repo.py all
Run one gate by naming it: skills, metadata, links, whitelist, agents,
sync, evidence, updater, or selftest. The script prints per-check PASS/FAIL lines and exits
non-zero on any failure.
What ships with it
2 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.
- 7d ago First seen · 93 lines · 36 tokens per session scan A 1d49856d7f92
mathodology-dev-test-release is a skill published in the GitHub repository sweetcornna/mathodology (172 stars, last pushed 8d ago), licensed MIT. It adds 36 tokens to every session and 1,028 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
release-verification
A release-verification checklist for software versions and packages. It covers changelogs, tests, packaging, installation smoke checks, version-control actions, publishing, and checks after release.
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
release-jetbrains
Use when releasing the Kilo JetBrains plugin -- resolve a version ("next rc" or explicit), run the prepare workflow, edit and commit a filtered human-readable changelog on the release PR, then watch publish to completion.
finishing-a-development-branch
A process for finishing a completed development branch. A branch is a separate line of code changes that can later be merged or submitted as a pull request.
goal-release
Cut a release end to end: use the draft-release skill to open the release PR and draft GitHub release, wait for CI to turn green, run the merge-pr skill to merge the release PR, then update the Homebrew formula from the published release assets. Use when the user wants to draft and merge a release in one go, or…
release-dry-run
Dry run for release: summarize changes since last release and suggest version bump.