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 Goldziher/basemind --skill poly-and-release-workflowgit clone --depth 1 https://github.com/Goldziher/basemindWrote 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/goldziher/basemind/poly-and-release-workflow)<a href="https://agentmods.dev/skills/goldziher/basemind/poly-and-release-workflow"><img src="https://agentmods.dev/badge/skills/goldziher/basemind/poly-and-release-workflow.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00007 | $0.00583 |
| Opus 5 | $0.00003 | $0.00292 |
| Sonnet 5 | $0.00001 | $0.00117 |
| Haiku 4.5 | $0.00001 | $0.00058 |
Grade A, and why
poly-and-release-workflow scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Poly + Release Workflow
The canonical order to run before pushing a change. Each step gates the next; do not skip.
Local check loop
cargo fmt
cargo clippy --workspace --all-targets --tests -- -D warnings
cargo test --workspace
poly lint .
Why this order:
cargo fmtfirst so clippy / poly don't fail on formatting.- Clippy strict (
-D warnings) — surface real issues before the broader poly sweep. - Unit + integration tests catch logic regressions before the slow harness.
poly lint .is the meta-linter: typos, markdownlint (120-char cap), cargo-deny licenses, cargo-machete unused deps, rustdoc-lint, rust-max-lines (1000-line cap onsrc/**/*.rs).
Harden harness
After the local loop passes:
BASEMIND_HARDEN_NO_BUILD=1 \
cargo test --release --test harden -- --ignored --nocapture \
2>&1 | tee /tmp/basemind-harden-$(date +%s).log
BASEMIND_HARDEN_NO_BUILD=1reusestarget/release/basemind— saves ~30s per run. Drop it when you're suspicious the binary is stale.- Expect 8/8 green: ripgrep, tokio, typescript, react, django, requests, gin, ripgrep-shallow.
- Canaries: tokio
spawn_hits >= 200, djangoget_hits >= 200, reactuseState_hits >= 20, ripgrep-shallowany_truncated == true.
Commit + push
- Conventional Commit prefix (
feat:,fix:,perf:,chore:,refactor:). - Body explains why. Mention schema bumps (
INDEX_SCHEMA_VER/ blob format) and added dependencies. - Co-author trailer per repo convention.
- Push directly to
mainis approved for the active iteration loop; PRs only when explicitly requested.
When something fails
- typos: fix the misspelling; prefer the dictionary correction unless it's a proper noun.
- markdownlint MD013 (line length > 120): split the line; for table cells, shorten the cell or move details to a code block under the table.
- cargo-deny license rejection: add the SPDX expression to
deny.toml'slicenses.allowonly if the license is genuinely permissive (Apache, MIT family, ISC, 0BSD, BSL, Unicode). Anything copyleft (GPL family) — escalate. - rust-max-lines: extract a submodule or helper file. Do not raise the cap.
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 · 53 lines · 7 tokens per session scan A c4ff618f48f0
poly-and-release-workflow is a skill published in the GitHub repository Goldziher/basemind (99 stars, last pushed 6d ago), licensed MIT. It adds 7 tokens to every session and 583 once invoked, about $0.0000 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
compiler-commit
Use when you want to verify compiler changes and commit with the correct convention. Runs tests, lint, and format, then commits with the [compiler] or [rust-compiler] prefix.
sem
Use sem to get entity-level (function/class/method) semantic diffs, impact analysis, blame, and dependency context from any Git repo. Trigger this skill whenever the user asks what changed in a commit or PR, wants to understand the blast radius of a change, needs to know who last modified a function, wants to trace…
sem
Semantic version control CLI. Entity-level diffs for Git (functions, classes, methods instead of lines).
commit
Auto-fix, lint, test, and commit changes with a conventional commit message.
vhs-e2e-gif
Record a test run, a TUI session, or any terminal command as a GIF with VHS and attach it to a GitHub PR as a release-hosted asset, never a repo commit. Use when asked to record an e2e run, demo a fix on a PR, attach a GIF or screen recording to a pull request, show a test passing visually, or produce a terminal…
056-design-avoid-breaking-changes
Use when you need to review a plan, OpenSpec change, specification, or implementation proposal for breaking-change risk across commands, skills, generated outputs, XML sources, README/docs, tests, CI, APIs, schemas, configuration, data, migration, and release guidance. This should trigger for requests such as Review…