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 iampantherr/SecureContext --skill developer-git-workflowgit clone --depth 1 https://github.com/iampantherr/SecureContextWrote 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/iampantherr/securecontext/developer-git-workflow)<a href="https://agentmods.dev/skills/iampantherr/securecontext/developer-git-workflow"><img src="https://agentmods.dev/badge/skills/iampantherr/securecontext/developer-git-workflow/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/iampantherr/securecontext/developer-git-workflow"><img src="https://agentmods.dev/badge/skills/iampantherr/securecontext/developer-git-workflow.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 | $0.00019 | $0.00519 |
| Opus 5 | $0.00010 | $0.00260 |
| Sonnet 5 | $0.00004 | $0.00104 |
| Haiku 4.5 | $0.00002 | $0.00052 |
Grade A, and why
developer-git-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 yesterday.
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
GIT WORKFLOW
(Extracted from roles.json deepPrompt for the developer role during the v0.19.0 role/skill split. Original content preserved verbatim. Edit freely; the mutator will propose improvements based on skill_runs telemetry once this skill is invoked by an agent.)
Atomic Commits: Each commit should represent one logical change. It should compile, pass tests, and be deployable on its own. If you're writing "and" in the commit message, split the commit.
Commit Messages: Format: imperative mood subject line under 72 characters. Body explaining why, not what — the diff already shows what changed. "Fix authentication token expiry calculation" is better than "Fixed bug." The body is for future-you at 2am during an incident trying to understand a git bisect result.
Branch Strategy: Feature branches off main. Short-lived (days, not weeks). Merge via PR with review. Delete after merge. Prefer rebase over merge for a clean history when working solo. Merge commits for team PRs to preserve review context.
Code Review Mindset (Giving): Your job is to understand the change and make the code better, not to demonstrate your knowledge. Ask questions before making statements. Separate blocking issues from suggestions. Never leave a PR with only approvals and no comments — you didn't read it.
Code Review Mindset (Receiving): PRs are not personal. Feedback is about the code, not you. Respond to every comment, even if just to acknowledge. "Addressed in commit X" is sufficient. Push back when you disagree — but with reasoning, not emotion. Approval without changes is not the goal.
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.
- yesterday First seen · 36 lines · 19 tokens per session scan A d17c5128b6a1
developer-git-workflow is a skill published in the GitHub repository iampantherr/SecureContext (8 stars, last pushed 2d ago), licensed MIT. It adds 19 tokens to every session and 519 once invoked, about $0.0001 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 2026-09-08.
Other skills, from other repositories
pr-review
Address feedback left on a GitHub pull request: fetch unresolved review threads, make agreed Elixir/Phoenix code fixes, reply, and resolve. Use for a PR URL/number or reviewer comments. NOT for pre-PR review, findings triage, or CI monitoring.
phx-pr-review
Address feedback left on a GitHub pull request: fetch unresolved review threads, make agreed Elixir/Phoenix code fixes, reply, and resolve. Use for a PR URL/number or reviewer comments. NOT for pre-PR review, findings triage, or CI monitoring.
github
Manage the full GitHub workflow from the terminal — auth, issues, pull request lifecycle (branch/commit/open/CI/merge), code review, and repo management. Uses the gh CLI when present, with a git + REST API fallback. Use when asked to "open a PR", "create an issue", "review this PR", "check CI", "list issues".
simplify
Use when the user says "simplify this diff" or asks for a compression pass over a change-set. Not for dead-code sweeps: use deslop.
make-pr-easy-to-review
Use when a human explicitly asks to reshape or annotate one pull request for review. Don't use for pushing the rewritten branch or mutating any remote.
review
Structured code review with parallel audit agents, confidence-scored triage, and optional auto-fix. Examines uncommitted changes, staged diffs, commit ranges, or specific paths. Produces a tiered report (MUST-FIX / RECOMMENDED / NIT) backed by evidence, then optionally applies fixes with verification.