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 agentmods add skills/matbanik/agentic-genomics/git-workflownpx skills add matbanik/agentic-genomics --skill git-workflowgit clone --depth 1 https://github.com/matbanik/agentic-genomicsWhat 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 | $0.00026 | $0.01435 |
| Opus 5 | $0.00013 | $0.00718 |
| Sonnet 5 | $0.00005 | $0.00287 |
| Haiku 4.5 | $0.00003 | $0.00144 |
Grade C, and why
Git Workflow scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
ssh-keygen -t ed25519 -C "[email protected]" -f "$HOME/.ssh/id_ed25519_signing" -N "" How it starts
The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Workflow Skill
Commit Policy
Do NOT
git commitorgit pushunless (a) the user explicitly directs it, or (b) it is a defined step in the approved plan/task. Never auto-commit at the end of a correction cycle or verification pass.
The One Rule
Run the script. Don't improvise git commands.
# // turbo pwsh -File .agent/skills/git-workflow/scripts/agent-commit.ps1 -Message "feat: description"The script validates signing config, stages, commits, pushes, and verifies — all in one command. If you skip the script, you WILL cause a hang.
Agent invocation rules:
- Set
WaitMsBeforeAsyncto 30000 (push can take 10-20s on large changesets) - If the command goes to background anyway, do NOT poll
command_status— rungit log --oneline -1directly to verify - Never issue more than one
command_statuscheck; if it shows no output, the command finished and output was lost — verify the result instead
Script Usage
# Basic commit + push to main
# // turbo
pwsh -File .agent/skills/git-workflow/scripts/agent-commit.ps1 -Message "feat: add new feature"
# With body text
# // turbo
pwsh -File .agent/skills/git-workflow/scripts/agent-commit.ps1 -Message "feat: add feature" -Body "Detailed description here"
# Push to a different branch
# // turbo
pwsh -File .agent/skills/git-workflow/scripts/agent-commit.ps1 -Message "fix: correct bug" -Branch "dev"
# Commit without pushing
# // turbo
pwsh -File .agent/skills/git-workflow/scripts/agent-commit.ps1 -Message "wip: save progress" -Push $false
What the Script Does (Do NOT Do These Manually)
- ✅ Validates SSH signing config (fails fast if GPG would hang)
- ✅ Checks remote URL format (warns on HTTPS)
- ✅ Stages all changes (
git add -A) - ✅ Commits with
-mflag (never opens editor) - ✅ Pushes to origin (unless
-Push $false) - ✅ Verifies with
git log --oneline -1
[!WARNING]
--no-verifyis a last resort. It skips ALL pre-commit hooks — not just gitleaks, but also JSON/YAML validation, private-key detection, and whitespace fixes. Use only when:
- Commits hang due to gitleaks scanning large binary files
- You have verified the staged files don't contain secrets
After a
--no-verifycommit, manually runpre-commit run --all-filesto catch anything skipped.
What ships with it
1 file 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.
- 2d ago First seen · 162 lines · 26 tokens per session scan C 6593b5a08709
Git Workflow is a skill published in the GitHub repository matbanik/agentic-genomics (2 stars, last pushed 3mo ago), licensed MIT. It adds 26 tokens to every session and 1,435 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
design-mcp-server
Design the tool surface, resources, and service layer for a new MCP server. Use when starting a new server, planning a major feature expansion, or when the user describes a domain/API they want to expose via MCP. Produces a design doc at docs/design.md that drives implementation.
add-tool
Scaffold a new MCP tool definition. Use when the user asks to add a tool, create a new tool, or implement a new capability for the server.
api-linter
MCP definition linter rules reference. Use when bun run lint:mcp or bun run devcheck reports a lint error or warning (format-parity, schema-is-object, name-format, server-json-, etc.) and you need to understand the rule, its severity, and how to fix it. Every rule ID the linter emits has an entry in this doc.
api-context
Canonical reference for the unified Context object passed to every tool and resource handler in @cyanheads/mcp-ts-core. Covers the full interface, its RequestContext base, all sub-APIs (ctx.log, ctx.state, ctx.requestInput, ctx.inputs, ctx.enrich, ctx.content), and when to use each.
api-canvas
DataCanvas primitive reference — a Tier 3 SQL/analytical workspace for tabular MCP servers, backed by DuckDB. Use when registering tables from upstream APIs, running ad-hoc SQL across them, and exporting results. Covers the acquire → register → query → export flow, per-table TTL, the token-sharing pattern for…
api-errors
McpError constructor, JsonRpcErrorCode reference, and error handling patterns for @cyanheads/mcp-ts-core. Use when looking up error codes, understanding where errors should be thrown vs. caught, or using ErrorHandler.tryCatch in services.