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 agentmods add commands/ruslan-korneev/claude-plugins/features-graphgit clone --depth 1 https://github.com/ruslan-korneev/claude-pluginsWhat 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 | $0.00014 | $0.01040 |
| Opus 5 | $0.00007 | $0.00520 |
| Sonnet 5 | $0.00003 | $0.00208 |
| Haiku 4.5 | $0.00001 | $0.00104 |
Grade A, and why
features: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 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 — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Command /feature-list:graph
Regenerate the Mermaid dependency graph in the features README.
Instructions
Step 1: Find All Feature Files
Use Glob to find all feature files:
docs/technical-requirements/features/*.md
Exclude:
README.md00-template.md
Step 2: Parse Feature Frontmatter
For each feature file, read and parse YAML frontmatter:
---
id: core-01
title: User Management
phase: core
status: completed
dependencies:
- integration-01
---
Extract:
id— Feature identifiertitle— Display namephase— Category for groupingstatus— For status icondependencies— Links to other features
Step 3: Validate Dependencies
Check each dependency exists:
all_ids = {f.id for f in features}
for feature in features:
for dep in feature.dependencies:
if dep not in all_ids:
warnings.append(f"{feature.id} → {dep} (not found)")
Check for circular dependencies:
# Use DFS to detect cycles
def has_cycle(node, visited, rec_stack):
visited.add(node)
rec_stack.add(node)
for dep in graph[node]:
if dep in rec_stack:
return True # Cycle detected
if dep not in visited and has_cycle(dep, visited, rec_stack):
return True
rec_stack.remove(node)
return False
Step 4: Generate Mermaid Graph
Build the Mermaid flowchart:
flowchart TD
subgraph Core
core-01[User Management ✅]
core-02[Product Catalog 🔄]
end
subgraph Workflow
workflow-01[Checkout 📝]
end
subgraph Integration
integration-01[Email Service ✅]
end
workflow-01 --> core-01
workflow-01 --> core-02
workflow-01 --> integration-01
Status icons:
✅— completed🔄— in_progress📝— draft
Step 5: Update README
Read docs/technical-requirements/features/README.md
Find the markers:
<!-- dependency-graph:start -->
...existing content...
<!-- dependency-graph:end -->
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 First seen · 233 lines · 14 tokens per session scan A 9a3caa724949
features:graph is a command published in the GitHub repository ruslan-korneev/claude-plugins (4 stars, last pushed 6mo ago), licensed MIT. It adds 14 tokens to every session and 1,040 once invoked, about $0.0001 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 commands, from other repositories
create-command
Create slash commands with brainstorming and best practices.
create-hook
Create hooks with brainstorming and security-first design.
improve-skills
Identify and implement skill improvements from execution logs and user evaluations.
validate-hook
Validate hooks for security, performance, and SDK compliance.
hooks-eval
Evaluate all hooks in a plugin for quality and compliance.
evaluate-skill
Manually evaluate a recent skill execution to record qualitative feedback.