Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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-worker-operations)<a href="https://agentmods.dev/skills/knuckles-team/repository-manager/repository-manager-worker-operations"><img src="https://agentmods.dev/badge/skills/knuckles-team/repository-manager/repository-manager-worker-operations/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-worker-operations"><img src="https://agentmods.dev/badge/skills/knuckles-team/repository-manager/repository-manager-worker-operations.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 | $0.00186 | $0.02925 |
| Opus 5 | $0.00093 | $0.01463 |
| Sonnet 5 | $0.00037 | $0.00585 |
| Haiku 4.5 | $0.00019 | $0.00293 |
Grade A, and why
repository-manager-worker-operations 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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Manager — Worker Operations
rm_remote_workers composes RMDD-15's remote-execution registry/staging/artifact
package with RMDD-08's CapacityInventory weighted resource ledger. It is the
governed surface for placing and staging work on a non-local host — it never
builds a raw shell string, never accepts a credential, and never lets a caller
assert same-node execution the tool cannot itself verify.
⚠ Read this before anything else: two actions deliberately fail closed today
Verified against agent-packages/repository-manager main at fdce825:
recheck(and any live remote dispatch) refuses without the optionaltunnel-managerdependency. Registration (register_worker/profile) never needs live inventory resolution, so the registry stays constructible withouttunnel-managerinstalled — but the dispatch-time entitlement check raises a namedRemoteExecutionUnavailableError(error_code: "dependency_blocked"), preserving the realImportErroras its cause, the moment inventory resolution is actually needed. Iftunnel-managerIS installed but no inventory resolver is configured for this entrypoint, the refusal says that instead — still a refusal, never a silent no-op.host_loss_reconcilealways refuses. Host-loss reconciliation requires a live, WorkItem-authoritativeResourceScheduler.release(repository_manager.native_reservations.NativeWorkItemReservationPort, bound to a connected graph-os engine client). As of this lane, grepping the whole package for that construction wired into any MCP/CLI entrypoint finds none — not this one, and not RMDD-28's sibling native lane authority either. This module deliberately never substitutes a local in-memory reservation ledger for that missing authority — doing so would itself be the "parallel job ledger / second store" the program's correctness constraints forbid.
Never work around either refusal with a raw SSH command, a hand-rolled credential, or a local reservation you invented — report the refusal and escalate.
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 · 206 lines · 186 tokens per session scan A b851cb588b45
repository-manager-worker-operations is a skill published in the GitHub repository Knuckles-Team/repository-manager (2 stars, last pushed 14d ago), licensed MIT. It adds 186 tokens to every session and 2,925 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
release-changelog-harness
Chooses ecosystem-native release and changelog tooling (Changesets, Melos, release-plz) plus binary distribution (GitHub Release tarballs, install.sh) when the product is an executable. Use for release CI, install.sh, versioning, CHANGELOGs, shipping MCP/CLI without clone, or meta repos that only ship skills via npx…
polish-docs-meta
Finalize documentation and project metadata for a ship-ready release. Use after implementation is complete, tests pass, and devcheck is clean. Safe to run at any stage — each step checks current state and only acts on what still needs work.
github-via-nyxid
Operate a user's GitHub account through NyxID's credential-brokering proxy (service slug api-github) — read and write repositories, files, issues, pull requests, commits, branches, Actions, gists and anything else the GitHub REST API exposes, all on the user's behalf and without ever handling a raw token. NyxID…
release-versioning
Discipline for release classification, version bumps, and changelogs, Conventional Commits classify the release range, SemVer computes the version from those commits, Keep a Changelog renders the result. Use when the user asks to cut a release, bump a version, write a changelog, decide if a change is a…
git-workflow
Git best practices for version control and collaboration.
memory-commit
Use when the user explicitly says "remember this", "save this", "ghi nho", "luu lai", "save for next time", or otherwise asks to persist the immediately preceding context. Captures with the appropriate contexttype (decision, preference, fact, skill, task, conversation) so future sessions can retrieve it accurately.