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-candidate-certificationgit 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-candidate-certification)<a href="https://agentmods.dev/skills/knuckles-team/repository-manager/repository-manager-candidate-certification"><img src="https://agentmods.dev/badge/skills/knuckles-team/repository-manager/repository-manager-candidate-certification/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-candidate-certification"><img src="https://agentmods.dev/badge/skills/knuckles-team/repository-manager/repository-manager-candidate-certification.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 | $0.01935 |
| Opus 5 | $0.00093 | $0.00967 |
| Sonnet 5 | $0.00037 | $0.00387 |
| Haiku 4.5 | $0.00019 | $0.00194 |
Grade A, and why
repository-manager-candidate-certification 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 10d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Manager — Candidate Certification
A candidate is one immutable branch submission offered for generation
formation; a generation is a sealed, ordered set of candidates with exact
certification and landing evidence. Both are typed contracts
(repository_manager.development.models.Candidate / Generation) that cross the
MCP/CLI/WorkItem/worker boundary — this skill teaches their vocabulary and the one
verification action pair (rm_concepts verify_candidate / verify_generation)
that reads them directly. There is no separate "form/seal/certify a generation"
MCP action — that lifecycle runs internally inside rm_merge_queue(action="run");
this skill names that honestly rather than inventing a tool surface that does not
exist.
When to use
- Explain what state a candidate or generation is in, and what that state requires.
- Verify one candidate's introduced
CONCEPT:markers against reserved claims before it lands (rm_concepts verify_candidate). - Verify every candidate in a sealed generation, including cross-candidate
collisions, before landing (
rm_concepts verify_generation). - Understand the evidence/refusal vocabulary a rejected or bisected generation reports.
When NOT to use
- Actually enqueue, watch, or land a branch →
repository-manager-merge-and-reconcile(rm_merge_queue) — that is where batching, differential gating, and bisection live and run. - Reserve a concept id before writing its marker →
repository-manager-concept-coordination(rm_concepts reserve). - Open/check/finish the lane that produced the candidate →
repository-manager-lane-lifecycle.
The vocabulary (read from results, never called as actions)
These are StrEnum wire values from repository_manager.development.enums that
appear inside rm_concepts/rm_merge_queue results — not a second action surface.
| Enum | Values | Meaning |
|---|---|---|
CandidateState |
queued, validating, ready, landing, landed, rejected, withdrawn, failed |
One candidate's lifecycle. A landing/landed candidate always carries its generation_id; a rejected/withdrawn/failed one always carries a reason. |
GenerationState |
open, sealed, integrating, certified, landing, landed, rejected, expired |
The sealed set's lifecycle. |
ValidationStage |
feedback, integration, certification, smoke, release |
Ordered validation confidence stages — a certification-stage PASSED evidence record always carries the exact generation_id it certifies. |
EvidenceOutcome |
passed, failed, skipped, refused |
One gate/evidence run's outcome. passed evidence never carries failure_ids. |
LandingOutcome |
landed, target_moved, refused, failed |
A fenced target-branch landing attempt's result. |
RefusalCode / FailureClass |
invalid_request, unauthorized_target, conflict_base_moved, capacity_disk_deferred, dependency_blocked, cancelled_deadline, worker_environment_failure, validation_candidate_failure, stale_fence_duplicate_effect, reconciliation_required, internal_error, plus refinements (path_outside_configured_root, invalid_git_ref, invalid_git_sha, remote_alias_required, remote_credentials_forbidden, shell_command_forbidden, resource_limit_invalid, invalid_state_combination, duplicate_request) |
Stable refusal categories shared by every public surface (C-10). |
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.
- 10d ago First seen · 129 lines · 186 tokens per session scan A 7dbba2312dce
repository-manager-candidate-certification is a skill published in the GitHub repository Knuckles-Team/repository-manager (2 stars, last pushed 13d ago), licensed MIT. It adds 186 tokens to every session and 1,935 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
trace-mcp-refactoring
Safe refactoring workflow using trace-mcp — assess risk, find candidates, check impact, and rename symbols across all files without missing import sites or cross-file references.
m1nd-first
Use when investigating a repository, searching for implementation, reviewing changes, working from specs/docs, or preparing a risky code change in an environment where m1nd is available. This doctrine makes m1nd the first investigative layer before grep, glob, or manual file reads, except when the task is pure…
review-thread
Record review verdicts and run the StateNote review thread on an agent-operation instance — every ReviewRequest verdict is one atomic batch-direct-write that advances status and co-writes a reviewnote explaining why, and findings are corrected by appending notes rather than editing them.
audit-architecture
Audit module coupling, cohesion, hidden dependencies, and design smells. Use when conducting architecture reviews, evaluating design decisions, or identifying structural tech debt.
find-bugs
Locate likely bug locations in code.
sumo-qa-planning-qa-rollout
Use when you have a chunk of QA work (a story, a PR, a strategy phase) that needs to be turned into a written plan of bite-sized, independently-executable tasks before any test code is written. Walks scope → file structure → bite-sized tasks → confirm, one section per turn. Produces docs/qa/plans/YYYY-MM-DD- .md ready…