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-concept-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-concept-coordination)<a href="https://agentmods.dev/skills/knuckles-team/repository-manager/repository-manager-concept-coordination"><img src="https://agentmods.dev/badge/skills/knuckles-team/repository-manager/repository-manager-concept-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-concept-coordination"><img src="https://agentmods.dev/badge/skills/knuckles-team/repository-manager/repository-manager-concept-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 | $0.00185 | $0.02071 |
| Opus 5.5 | $0.00074 | $0.00828 |
| Sonnet 5.5 | $0.00037 | $0.00414 |
| Haiku 4.5 | $0.00018 | $0.00207 |
Grade A, and why
repository-manager-concept-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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Manager — Concept Coordination
rm_concepts_* is repository-manager's thin, MCP/CLI-neutral consumer of RMDD-16's
central concept-id claim authority (agent_connector_sdk.governance. concept_reservation). Repository-manager never allocates a concept id itself —
every action here is a claim/verification call against an injected authority port.
⚠ Read this before anything else: the authority is unavailable on main today
As of this lane (verified 2026-08-10 against agent-packages/repository-manager
main at fdce825), RMDD-16's authority module is not an ancestor of
agent-connector-sdk main. Every mutating rm_concepts_* action —
reserve/get/list/release/materialize/verify_candidate/verify_generation
— therefore refuses with a named ConceptAuthorityUnavailable refusal
(error_code: "dependency_blocked" from the shared RefusalCode/FailureClass
vocabulary), preserving the real ImportError as its cause. This is not a bug and
not this skill's cue to route around it:
- Never substitute a local, in-memory, or fixture allocator for the real
authority to "unblock" a demo —
repository_manager.concept_actions. build_default_concept_authority()is a deliberate best-effort probe that returnsNone(never a fabricated authority) whenever the module is absent, exposes no documented live-construction entrypoint, or construction itself raises. - Report the refusal truthfully —
{"ok": false, "refused": "...", "error_code": "dependency_blocked", "unreachable": ...}— rather than describing concept coordination as working. - This will change the moment RMDD-16's authority lands on agent-connector-sdk
main; re-verify this section against the live server before trusting it stale.
When to use
- Before writing a new
CONCEPT:marker in code/docs, so two sessions never collide on the same identifier (reserve). - Checking or listing existing claims (
get/list). - Releasing a claim that was never actually used (
release). - Promoting a claim from reserved to in-use (
materialize). - Verifying one candidate's or one sealed generation's introduced
CONCEPT:markers against reserved claims, including cross-candidate collisions (verify_candidate/verify_generation). - A read-only drift report across the authority/fragment/view/source layers
(
reconcile).
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 Changed · +1 tokens per session 1f0527556fcb
- 2mo ago First seen · 150 lines · 184 tokens per session scan A 8b0a02596904
repository-manager-concept-coordination is a skill published in the GitHub repository Knuckles-Team/repository-manager (3 stars, last pushed today), licensed MIT. It adds 185 tokens to every session and 2,071 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
release
MUST READ before preparing a release commit or GitHub release -- the blocking GitHub preflight (dev/releasepreflight.py), project.save() versioning, changelog, README, template sync verification, fresh-install smoke, and the post-push GitHub release procedure (references/github-release.md).
merge-divergent-tox
Merge or compare two divergent TouchDesigner .tox/.toe binaries that git cannot three-way-merge. Load when a merge/rebase conflicts on a .tox or .toe, when asked to merge, port, reconcile, or diff two versions of a TD component, or when comparing a component across branches, machines, or TD builds.
servicenow-studio-gitlab-app
Wire a ServiceNow scoped app (App Engine Studio / Fluent) to a GitLab repository and drive its promotion two ways — Path A: native Studio source control (servicenowsourcecontrol → importrepository / applyremotesourcecontrolchanges, handing off to servicenowcicd for publish/install), or Path B: GitLab-CI-driven…
gitlab-merge-request-review
Review and merge GitLab merge requests via the gitlab-api MCP server — by default the MRs assigned to you or where you are a reviewer, optionally scoped to a project, group, or the whole instance. Read an MR, gate it on a green pipeline (pipeline → jobs → job log), then approve, accept/merge, or set…
gitlab-merge-request-create
Open a new GitLab merge request against a project via the gitlab-api MCP server — from a source branch into a target branch, with title, description, assignees, reviewers, labels, and remove-source-branch/squash options. Use when the agent must create/open an MR for a project. Do NOT use to review, approve, or merge…
gitlab-api-operations
Operate gitlab-api through its governed MCP and Arbora capabilities, including gitlab issues, gitlab merge request create, gitlab merge request review, gitlab pipelines, gitlab vulnerabilities. Use when a request requires this provider's read, change, automation, ingestion, troubleshooting, or evidence workflows.