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 intent-driven-dev/intent-driven-template --skill openspec-git-disciplinegit clone --depth 1 https://github.com/intent-driven-dev/intent-driven-templateWrote 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/intent-driven-dev/intent-driven-template/openspec-git-discipline)<a href="https://agentmods.dev/skills/intent-driven-dev/intent-driven-template/openspec-git-discipline"><img src="https://agentmods.dev/badge/skills/intent-driven-dev/intent-driven-template/openspec-git-discipline/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/intent-driven-dev/intent-driven-template/openspec-git-discipline"><img src="https://agentmods.dev/badge/skills/intent-driven-dev/intent-driven-template/openspec-git-discipline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 57 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00041 | $0.00646 |
| Opus 5.5 | $0.00016 | $0.00258 |
| Sonnet 5.5 | $0.00008 | $0.00129 |
| Haiku 4.5 | $0.00004 | $0.00065 |
Grade A, and why
openspec-git-discipline 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenSpec Git Discipline
Core Rule
Every OpenSpec state change must cross main before the next lifecycle phase depends on it.
- Propose/continue artifacts may be drafted on a branch, but must be committed and merged to
mainbefore apply starts. - Apply may run on
main, a branch, or a worktree only if that exact proposal change is already available onmain. - Archive may run only from
mainafter implementation is merged back.
Never create commits, branches, or merges unless the user explicitly asks.
Gates
| Moment | Gate |
|---|---|
| Before propose | Prefer main; if not, warn and ask whether to continue intentionally. |
| During continue | Before creating the next artifact, ask the user to commit completed artifact changes or explicitly continue without that checkpoint. |
| After propose | Ask the user to commit proposal artifacts; offer to create a PR branch for review. |
| Before apply | Confirm the proposal change is committed on main; then apply may run from main, a branch, or a worktree. |
| Before archive | Stop unless implementation is merged back to main and archive is running from main. |
| After archive | Ask the user to commit archive/spec sync changes. |
Required Checks
Before apply:
- Run
git status --short. - Verify
openspec/changes/<change>/has no uncommitted proposal files. - Verify the proposal change exists on
mainbefore applying from any branch/worktree.
Use this language if the proposal has not reached main:
I should not apply this yet because the proposal change has not reached
main. A proposal can be drafted on a branch, but apply must start only after that proposal state is available onmain. Please merge or commit the proposal tomainfirst, then I can apply frommain, a branch, or a worktree.
Before archive:
- Run
git branch --show-currentandgit status --short. - Stop if not on
main. - Stop if implementation work has not been merged back to
main.
Use this language:
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 First seen · 62 lines · 41 tokens per session scan A a5d5bcbfaaa9
openspec-git-discipline is a skill published in the GitHub repository intent-driven-dev/intent-driven-template (169 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 646 once invoked, about $0.0002 per session on Opus 5.5. 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-archivist
Close out a spec-superflow change with verification, summary, and archive readiness. Invoke when implementation is complete, verification is underway, or the user asks for a final wrap-up.
release
Verify, write the CHANGELOG, cut a version — then hand the release sequence back.
pr-stack
Plan and execute splitting a large PR or branch into a reviewable stacked PR sequence.
pr-review
Intent-aware map-reduce PR review with CI/CD support, confidence gating, and intelligent comment deduplication.
pr-walkthrough
Generate an evidence-grounded markdown walkthrough for a pull request.
publish-artifact
Publish an rp1 artifact (investigation report, design doc, audit) from .rp1/work/ as an idempotent PR or issue comment instead of committing it to the repo; re-runs update the same comment in place.