Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add sigistry/marketplace/plugin install recordsWrote 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/commands/sigistry/marketplace/init-ci)<a href="https://agentmods.dev/commands/sigistry/marketplace/init-ci"><img src="https://agentmods.dev/badge/commands/sigistry/marketplace/init-ci.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 5.1 | $0.00011 | $0.00306 |
| Opus 5 | $0.00005 | $0.00153 |
| Sonnet 5 | $0.00002 | $0.00061 |
| Haiku 4.5 | $0.00001 | $0.00031 |
Grade A, and why
init-ci 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 3d 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.
What it actually says
Initialize Records FHIR Validation CI
Use the fhir-ci-quality skill and read skills/fhir-validation/references/quality-rules.md plus skills/fhir-validation/references/ci-templates.md when needed.
Target resource directory: $ARGUMENTS or infer from detector output.
Use this helper for a first draft when the target repository does not already have a better workflow pattern:
node "${CLAUDE_PLUGIN_ROOT}/skills/fhir-validation/scripts/generate-ci.mjs" --dir "$ARGUMENTS"
Steps:
- Run the detector script to find source directories, generated directories, package scripts, and existing
.github/workflows. - Prefer an existing repository package manager and validation script if present.
- Add a GitHub Actions workflow only when the repository has no suitable validation workflow.
- Use
records validate-file <resource-directory> --format junitfor local CLI validation. - Use
records --api-url "$RECORDS_API_URL" --auth-token "$RECORDS_API_KEY" ...only when the user asks for API-backed validation. - Add an explicit CLI install step if the repository does not already install Records.
Do not add Firely, HAPI, Java validator, SUSHI, or external terminology services unless the user asks for that validator and consents to the installation/network boundary.
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.
- 3d ago First seen · 28 lines · 11 tokens per session scan A b44a706e1e9d
init-ci is a command published in the GitHub repository sigistry/marketplace (3 stars, last pushed 3d ago), licensed MIT. It adds 11 tokens to every session and 306 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 2026-09-03.
Other commands, from other repositories
validate
Mechanically validate the sonu plugin repo before a PR — manifest sync, YAML frontmatter, shell-fence syntax, named-source and AI-attribution scans, cross-reference integrity, skill reachability. Only meaningful inside the claude-plugins repo; in any other repo, say so and stop.
matrix-cell-onboard
Add a new PHP/Laravel/PHPUnit/Monolog cell to a multi-major library's CI matrix. Walks composer constraints, workflow YAML, Testbench mapping, polyfill branch coverage, dual-testsuite gating, and a local dry-run. Use when extending support to a new runtime version, restoring a previously dropped cell, or onboarding a…
f5-gate
Quality gate management with evidence collection.
_test-shared
Shared testing patterns and templates (internal).
engineer
Guided full-project lifecycle - walks intake → plan (sign-off) → autonomous build → quality gates → CI/finish, invoking the right claude-engineer skill at each stage.
check-01-happy
Le wiki est dans un état sain : toutes les pages ont un frontmatter valide, les liens [[wikilinks]] pointent vers des pages existantes, index.md est à jour et aucune page n'est orpheline. La commande /check doit produire un rapport propre et mettre à jour wiki/log.md. Elle ne doit rien modifier dans le wiki au-delà du…