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 Knuckles-Team/repository-manager --skill repository-manager-build-coordinationgit clone --depth 1 https://github.com/Knuckles-Team/repository-managerWrote 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/knuckles-team/repository-manager/repository-manager-build-coordination)<a href="https://agentmods.dev/skills/knuckles-team/repository-manager/repository-manager-build-coordination"><img src="https://agentmods.dev/badge/skills/knuckles-team/repository-manager/repository-manager-build-coordination/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/knuckles-team/repository-manager/repository-manager-build-coordination"><img src="https://agentmods.dev/badge/skills/knuckles-team/repository-manager/repository-manager-build-coordination.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 | $0.00187 | $0.02015 |
| Opus 5 | $0.00093 | $0.01007 |
| Sonnet 5 | $0.00037 | $0.00403 |
| Haiku 4.5 | $0.00019 | $0.00201 |
Grade A, and why
repository-manager-build-coordination 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 12d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Manager — Build Coordination
rm_build is a content-addressed build broker for any repository
(CONCEPT:RM-TASK-LEDGER). The dedup is the entire value: N lanes each asking for
the same build today each pay for a full cargo/pnpm build into their own
target-isolated/node_modules — measured at 21.7 GB across 4 duplicate
directories in this workspace after pruning. This tool publishes named artifacts to
one shared, checksummed cache instead.
When to use
- Request a build and get back either an already-published artifact set or a fresh
build (
request) — a second request for the same key waits on and reuses the first's result instead of rebuilding. - Check whether a key is cached without triggering a build (
status). - Fetch the published artifact list for a cache key (
artifacts). - Find out why a key did NOT hit cache — the exact differing component
(
explain). - Reclaim old cache entries under a bound (
gc).
When NOT to use
- Python project install/build via
pyproject.toml(rm_projectsinstall/build) →repository-manager-workspace-validation. - The merge queue's own gate execution (it calls a repo's declared command directly,
not this broker) →
repository-manager-merge-and-reconcile. - Deciding how many heavy builds a wave may run concurrently →
repository-manager-fleet-scale-operations.
Tools & actions
| Condensed tool | Actions |
|---|---|
rm_build |
request, status, artifacts, explain, gc |
CLI: repository-manager --build-broker {request,status,artifacts,explain,gc} --repo-path <repo>
with --build-spec / --build-key / --same-node / --build-wait-timeout /
--build-keep-recent / --build-max-age-days.
Key parameters
repo_path— any working tree of the target repository (defaults to the server's cwd).spec— which declared build spec to use from.buildcache.yaml(defaults to the repo's first).key— a cache key, forstatus/artifacts/explain.wait_timeout— secondsrequestwaits on an in-flight build of the same key before building anyway.keep_recent/max_age_days— forgc: always keep this many most-recent entries; reclaim anything else older than this, subject tokeep_recent.
What ships with it
2 files 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.
- 12d ago First seen · 153 lines · 187 tokens per session scan A b67c03bb28d3
repository-manager-build-coordination is a skill published in the GitHub repository Knuckles-Team/repository-manager (2 stars, last pushed 14d ago), licensed MIT. It adds 187 tokens to every session and 2,015 once invoked, about $0.0009 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
verifying-compose-ui
Verifying Compose UI by rendering components or previews and inspecting the resulting images and state transitions. Activate for visual behavior that requires runtime rendering; use ordinary tests for nonvisual logic.
interacting-with-project-runtime
Interacting with a project's JVM runtime through the Kotlin REPL to execute focused probes against project classes and dependencies. Activate when behavior must be observed by running code; use using-gradle for build inspection or task execution.
ingest-gradle-upgrade
Ingests a Gradle wrapper upgrade for this repository: reads the release notes, upgrade guides, and linked documentation for the version upgraded to, then updates this repo's own code/tooling and the shipped Gradle MCP skills (src/main/skills/) so everything stays accurate for that version. Positive Triggers (when to…
authoring-gradle-builds
Authoring and modifying Gradle build logic, including settings, plugins, dependencies, tasks, conventions, and upgrades. Activate when build files or plugins must change; use using-gradle for inspection or execution without build-definition edits.
using-gradle
Using Gradle MCP tools to inspect and run existing builds, including projects, tasks, properties, dependencies, and build results. Activate for Gradle build operation and diagnosis; use authoring-gradle-builds when the build definition itself must change.
advanced-gradle-dependencies
Analyzing advanced Gradle dependency behavior, including resolution, variants, capabilities, conflicts, constraints, and publication metadata. Activate for dependency-resolution design or diagnosis; use authoring-gradle-builds for routine dependency declarations.