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 AstravueOrg/astravue-mcp-server --skill mapping-dependenciesgit clone --depth 1 https://github.com/AstravueOrg/astravue-mcp-serverWrote 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/astravueorg/astravue-mcp-server/mapping-dependencies)<a href="https://agentmods.dev/skills/astravueorg/astravue-mcp-server/mapping-dependencies"><img src="https://agentmods.dev/badge/skills/astravueorg/astravue-mcp-server/mapping-dependencies/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/astravueorg/astravue-mcp-server/mapping-dependencies"><img src="https://agentmods.dev/badge/skills/astravueorg/astravue-mcp-server/mapping-dependencies.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 | $0.00061 | $0.00463 |
| Opus 5 | $0.00030 | $0.00231 |
| Sonnet 5 | $0.00012 | $0.00093 |
| Haiku 4.5 | $0.00006 | $0.00046 |
Grade A, and why
mapping-dependencies 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.
What it actually says
Mapping Dependencies
Build the dependency graph, then reason over it. The analysis (critical path, blockers, cycles) is deterministic and the most valuable part — teams rarely compute it by hand. This skill is read-only by default; only change dependencies when explicitly asked.
Workflow
-
Load the graph
astravue_list_project_tasks— the tasks (status, due dates) for the scopeastravue_list_dependencies— the blocking relationships
Confirm the project first if unclear (
astravue_list_projects). -
Analyze
From the edges, compute:
- Cycles — any A→B→…→A loop. Surface these first; a cyclic graph has no valid order and usually signals a modeling mistake.
- Critical path — the longest chain of dependent tasks. Its length drives the project's earliest finish; slipping any task on it slips the whole project.
- Blocked tasks — tasks whose blockers aren't done yet, especially those blocking many others.
-
Present the picture
Lay out the critical path as an ordered chain, list blocked tasks with what they're waiting on, and call out any cycles loudly. Use
astravue_preview_project_overvieworastravue_preview_task_listif a visual view helps the user. -
Change dependencies only on request
If the user wants to fix sequencing:
astravue_add_dependency/astravue_remove_dependency— adjust edges- Re-check for cycles after each change and confirm before applying.
Important
- Detect and report cycles before anything else — they make ordering and critical-path meaningless.
- The critical path is the longest dependent chain, not the count of dependencies.
- Default to read-only; only add or remove dependencies when the user explicitly asks.
- After any edge change, re-validate that no cycle was introduced.
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 · 42 lines · 61 tokens per session scan A 233470e6a4a3
mapping-dependencies is a skill published in the GitHub repository AstravueOrg/astravue-mcp-server (12 stars, last pushed 16d ago), licensed Apache-2.0. It adds 61 tokens to every session and 463 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
pm-init
Skill "pm-init" from wei63w/pm-manager, covering user input, outline, 1. scaffold, 2. lifecycle and type and 3. detect spec kit (required).
pm-all
Skill "pm-all" from wei63w/pm-manager, covering user input, outline and shared workflow (all /pm- commands).
pm-arch
Skill "pm-arch" from wei63w/pm-manager, covering user input, outline, done when and shared workflow (all /pm- commands).
pm-charter
Create, import, discover, approve, or skip project charter. No-arg form is an interactive wizard.
pm-done
Skill "pm-done" from wei63w/pm-manager, covering user input, outline and shared workflow (all /pm- commands).
pm-export
Export desensitized governance summary markdown for sharing or machine switch.