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 easingthemes/dx-aem-flow --skill dx-discover-reposgit clone --depth 1 https://github.com/easingthemes/dx-aem-flowWrote 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/easingthemes/dx-aem-flow/dx-discover-repos)<a href="https://agentmods.dev/skills/easingthemes/dx-aem-flow/dx-discover-repos"><img src="https://agentmods.dev/badge/skills/easingthemes/dx-aem-flow/dx-discover-repos/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/easingthemes/dx-aem-flow/dx-discover-repos"><img src="https://agentmods.dev/badge/skills/easingthemes/dx-aem-flow/dx-discover-repos.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 | $0.00048 | $0.01698 |
| Opus 5.5 | $0.00019 | $0.00679 |
| Sonnet 5.5 | $0.00010 | $0.00340 |
| Haiku 4.5 | $0.00005 | $0.00170 |
Grade A, and why
dx-discover-repos 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 2d 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.
dx-discover-repos
Resolve the set of repos a work item touches and emit a structured JSON array the KAI-HUB router uses to fan a worker pipeline out — one run per repo.
This skill is the multi-repo brain of the hub model. Single-repo projects never call it: their worker fires directly via its own webhook (dual-mode workers).
Inputs
| Input | Source | Notes |
|---|---|---|
workItemId |
skill argument | the ticket being routed |
| trigger-comment text | .ai/run-context/trigger-comment.txt if present, else fetch from the work item |
the human comment that fired the hook (after @kai-<agent>) |
| repo registry | $DX_REPOS_REGISTRY (default .ai/automation/registries/repos.json) |
alias → metadata; see dx-hub/shared/registry-format.md |
Output (StructuredOutput)
A JSON array, constrained to known registry aliases — never invent repos:
[
{ "alias": "brand-one", "repoId": "…", "adoProject": "Example Project",
"cloneUrl": "https://…/_git/brand-one", "branch": "development",
"reason": "explicit 'repos:' directive in trigger comment" }
]
On ambiguity or no match the skill emits a structured error object instead of an array, which the hub turns into a clarification comment on the work item:
{ "error": "ambiguous", "code": 3, "message": "project spans 2 platforms — add 'platform:' …" }
{ "error": "no-match", "code": 8, "message": "no candidate repo matched platform=… scope=… brand=…" }
The cascade
First non-empty tier wins. Tiers 0–2 are deterministic (fully testable offline); tier 3 is the LLM fallback, constrained to registry aliases.
digraph discover {
"Start" [shape=box];
"Tier 0: explicit repos: directive?" [shape=diamond];
"Tier 1: simple block present?" [shape=diamond];
"Tier 1 route ok?" [shape=diamond];
"Tier 2: cross-repo table?" [shape=diamond];
"Tier 3: LLM choose from registry" [shape=box];
"Emit JSON array" [shape=doublecircle];
"Emit structured error" [shape=doublecircle];
"Start" -> "Tier 0: explicit repos: directive?";
"Tier 0: explicit repos: directive?" -> "Emit JSON array" [label="non-empty"];
"Tier 0: explicit repos: directive?" -> "Tier 1: simple block present?" [label="empty"];
"Tier 1: simple block present?" -> "Tier 1 route ok?" [label="yes"];
"Tier 1: simple block present?" -> "Tier 2: cross-repo table?" [label="no"];
"Tier 1 route ok?" -> "Emit JSON array" [label="repos resolved"];
"Tier 1 route ok?" -> "Emit structured error" [label="exit 3 / exit 8"];
"Tier 2: cross-repo table?" -> "Emit JSON array" [label="non-empty"];
"Tier 2: cross-repo table?" -> "Tier 3: LLM choose from registry" [label="empty"];
"Tier 3: LLM choose from registry" -> "Emit JSON array";
}
What ships with it
10 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.
- scripts/parse-crossrepo-table.sh 3.4 KB runs code
- scripts/parse-explicit-repos.sh 3.3 KB runs code
- scripts/route-targets.sh 6.1 KB runs code
- tests/fixtures/comment-explicit.txt 84 B
- tests/fixtures/comment-no-repos.txt 48 B
- tests/fixtures/config-multi-platform.yaml 486 B
- tests/fixtures/config-single-platform.yaml 98 B
- tests/fixtures/repos-registry.json 405 B
- tests/fixtures/research-crossrepo.md 300 B
- tests/run-tests.sh 7.1 KB runs code
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.
- 2d ago Changed · -1 lines · -20 tokens per session 0928a6b9e749
- 1mo ago First seen · 151 lines · 68 tokens per session scan A d3c19223b109
dx-discover-repos is a skill published in the GitHub repository easingthemes/dx-aem-flow (6 stars, last pushed 2d ago), licensed MIT. It adds 48 tokens to every session and 1,698 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
story-readiness
Is a story implementation-ready? Checks clear acceptance criteria, open questions, ADR refs. READY/NEEDS WORK/BLOCKED/NOT ASSESSED.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
handle-linkedin-connection-request-signal
Use this skill when someone sends a team member an inbound LinkedIn connection request. An inbound request is a deliberate, ACTIVE first-party intent signal — meaningfully stronger than a passive profile view — and it deserves different scoring rules. The skill resolves and enriches the requester, gates them through…