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/obsidian-owl/specwright/gate-buildnpx skills add Obsidian-Owl/specwright --skill gate-buildgit clone --depth 1 https://github.com/Obsidian-Owl/specwrightWrote 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/obsidian-owl/specwright/gate-build)<a href="https://agentmods.dev/skills/obsidian-owl/specwright/gate-build"><img src="https://agentmods.dev/badge/skills/obsidian-owl/specwright/gate-build.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 | $0.00051 | $0.00808 |
| Opus 5 | $0.00026 | $0.00404 |
| Sonnet 5 | $0.00010 | $0.00162 |
| Haiku 4.5 | $0.00005 | $0.00081 |
Grade A, and why
gate-build 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 4d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gate: Build
Goal
Confirm the codebase compiles and tests pass across all configured tiers. This is the most basic gate — if the code doesn't build or tests don't pass, nothing else matters.
Inputs
{projectArtifactsRoot}/config.json--commands.build,commands.test,commands.test:integration,commands.test:smoke{repoStateRoot}/work/{selectedWork.id}/workflow.json-- selected work unit for evidence path
Outputs
- Evidence file at
{workDir}/evidence/build-report.md - Gate status update in the selected work's
workflow.json: PASS, FAIL, WARN, or SKIP - Console output showing results inline (users see findings, not just badges)
Constraints
Tiered Execution (LOW freedom):
Run tiers in execution order: commands.build → commands.test →
commands.test:integration → commands.test:smoke. Each tier runs only if the
previous tier passes (any tier failure stops further execution).
- If a tier's command is null or not configured, that tier produces SKIP. Emit an INFO note for each unconfigured tier — visibility rule: display the unconfigured tier name so users know what was skipped.
- If all tier commands are null/unconfigured, gate status is SKIP.
- Timeout: 5 minutes per command. If exceeded, status is ERROR.
Per-Tier Verdicts (LOW freedom):
| Tier | Failure verdict |
|---|---|
commands.build |
FAIL |
commands.test |
FAIL (test failure = FAIL) |
commands.test:integration |
FAIL (integration failure = FAIL) |
commands.test:smoke |
WARN (smoke produces WARN on failure — charter exception: quality gates default to FAIL: smoke tests validate optional end-to-end paths; degraded smoke is advisory, not blocking) |
Unconfigured tier = SKIP.
Evidence (LOW freedom):
Follow protocols/evidence.md. Evidence starts with a tier layout header
summarizing configured tiers and their run order. Each tier produces its own
evidence section containing: command executed (capture command run), exit code,
stdout/stderr output, and duration (elapsed wall time). Per-tier sections are
written regardless of tier outcome.
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.
- 4d ago First seen · 88 lines · 51 tokens per session scan A 25fa60b56b0f
gate-build is a skill published in the GitHub repository Obsidian-Owl/specwright (9 stars, last pushed 4mo ago), licensed MIT. It adds 51 tokens to every session and 808 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
rust-skills
Rust best practices — 179 rules across 14 categories for idiomatic, optimized Rust code.
new-skill
Scaffold a new brooks-lint analysis skill so it passes npm run validate and npm run evals on the first try — generates skills/{name}/SKILL.md (with the mandatory "Do NOT trigger for:" clause and a Process section citing guide step ranges) plus skills/{name}/{name}-guide.md (sequentially numbered steps), then appends…
cco-task
Organize work by task, track tokens/cost per task, and keep a small patchable execution state that is re-injected after /compact (SKILL.state-style) — start a task, patch its state, list tasks, or mark the active one done. Pairs with /cco-pack to load minimal context per task.
cco-templates
Manage context templates for common task types.
discuss
Use when exploring a feature idea before committing, or revisiting a parked one. Triggers — "/engineer.discuss", "/engineer.discuss ", "I have an idea about", "should we build", "let's think about".
prompt-tuning
Tune a prompt, or anything whose quality is measured by non-deterministic model output, without chasing noise - a noise baseline before the first edit, medians over repeated runs, enforcement AFTER generation rather than in the wording. Use when iterating on prompts or model-judged output.