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 closedloop-ai/claude-plugins --skill prd-dependency-graphgit clone --depth 1 https://github.com/closedloop-ai/claude-pluginsWrote 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/closedloop-ai/claude-plugins/prd-dependency-graph)<a href="https://agentmods.dev/skills/closedloop-ai/claude-plugins/prd-dependency-graph"><img src="https://agentmods.dev/badge/skills/closedloop-ai/claude-plugins/prd-dependency-graph/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/closedloop-ai/claude-plugins/prd-dependency-graph"><img src="https://agentmods.dev/badge/skills/closedloop-ai/claude-plugins/prd-dependency-graph.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 | $0.00210 | $0.05144 |
| Opus 5.5 | $0.00084 | $0.02058 |
| Sonnet 5.5 | $0.00042 | $0.01029 |
| Haiku 4.5 | $0.00021 | $0.00514 |
Grade A, and why
prd-dependency-graph 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 today.
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 — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ticket dependency graph
Turns a scope's tickets and their BLOCKS links into an interactive HTML graph. Two scripts do all the work, so every run is deterministic and every link is drawn:
scripts/refresh_server.pyreads the ClosedLoop REST API, builds the graph data, and writes the page. It is also the local helper behind the refresh button.scripts/render_graph.pydraws the graph, and embeds the graph's config in it.
Your job is to pick the scope and options, run them, name the columns, and check the result.
Inputs
- A scope slug:
- a PRD or other document (
PRD-751,ISS-6251): its PRODUCES children. A document with no ticket children (for example a single ticket) graphs itself and its neighbours. - a project (
PRO-67): every ticket in the project. The graph looks the same either way.
- a PRD or other document (
- Optional:
- output path. The default is
~/Desktop/<slug-lowercase>-dependency-graph.html. - whether to embed the graph into an existing HTML report instead of writing a standalone page.
- how far to follow outside blockers: the default is one layer, or
allfor the whole chain. - whether to include implementation plans. They are off by default because they are not work items and would double every ticket.
- output path. The default is
What counts as a dependency
- BLOCKS links are drawn as solid arrows. The source blocks the target, and the target waits on it.
- A BLOCKS arrow is red while its blocker is still open (any status other than DONE, CANCELED, EXECUTED, OBSOLETE or APPROVED), and grey once the blocker is finished. Box borders still show each ticket's own status, so a red border means the status is BLOCKED.
- The scope document (a PRD or other document with ticket children) is drawn as the root box, with a dotted PRODUCES arrow to each in-scope ticket. A project scope has no root. PRODUCES arrows are not counted as BLOCKS links.
- RELATES_TO and other link types are never drawn, even when a ticket reads like a blocker. If the user expects a dependency the graph does not show, check the link type with the API and tell them. Changing a link in ClosedLoop is the user's call.
- Tickets outside the scope are drawn dashed, and the legend reads "outside ":
- tickets that in-scope tickets block are shown one layer deep;
- tickets that block the scope are followed upstream
outside_blockers_depthlayers (default 1;"all"follows the chain to its roots).
What ships with it
4 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.
- today Changed · +40 lines · +25 tokens per session d57f3f97cac0
- 4d ago First seen · 169 lines · 185 tokens per session scan A 822460d5c9b4
prd-dependency-graph is a skill published in the GitHub repository closedloop-ai/claude-plugins (122 stars, last pushed today), licensed Apache-2.0. It adds 210 tokens to every session and 5,144 once invoked, about $0.0008 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 2026-10-16.
Other skills, from other repositories
kanban-video-orchestrator
Plan and run multi-agent video production pipelines.
sdlc-review
Review Kanban handoffs and route verified outcomes.
docs-governance
Route broad documentation-governance requests to existing ECC skills and run an opt-in, read-only audit of mapped documentation roles, links, ADR indexes, and evidence references. Use when a user asks for documentation governance, project-knowledge organization, documentation integrity, or a deterministic docs audit…
parallel-feature-development
Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…
bazel-build-optimization
Optimize Bazel builds for large-scale monorepos. Use when configuring Bazel, implementing remote execution, or optimizing build performance for enterprise codebases.
track-management
Use this skill when creating, managing, or working with Conductor tracks - the logical work units for features, bugs, and refactors. Applies to spec.md, plan.md, and track lifecycle operations.