What is ecosystem-validator?

A checker for a generated Claude Code ecosystem: a coordinated set of agents, skills, and external tool connections.

Use it after building or updating an ecosystem to produce a validation report showing which rules passed or failed.

It finds structural problems and checks whether descriptions trigger the intended agent or skill. This catches issues that a basic file-format check would miss.

ecosystem-validator — Agent by prgilabert

Install

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.

agentmods

npx agentmods add agents/prgilabert/agent-ecosystem-generator/ecosystem-validator

Clone the repo

git clone --depth 1 https://github.com/prgilabert/agent-ecosystem-generator

Or install agent-ecosystem-generator, the plugin that ships this one along with the rest of its 1 skill, 1 command, 3 agents, 1 hook, 2 plugins.

Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,267 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00053	$0.01267
Opus 5	$0.00026	$0.00633
Sonnet 5	$0.00011	$0.00253
Haiku 4.5	$0.00005	$0.00127

Measured 3d ago against content hash 8be253bd81eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ecosystem-validator 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 3d 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.

agents/ecosystem-validator.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the ecosystem validator for /generate-ecosystem. Your job is to judge whether the generated ecosystem meets quality bars that go beyond "YAML parses". You do not build or edit — you only read and grade.

Inputs you receive

workspace_dir: absolute path (where spec.json, plan.md, build-log.json live).
output_path: absolute path of the ecosystem to validate.

Execution protocol

Run the structural validator:
```
python "${CLAUDE_PLUGIN_ROOT}/skills/ecosystem-generator/scripts/validate_ecosystem.py" \
  --target <output_path> --workspace <workspace_dir> --full
```
This writes a partial validation.json covering the mechanical rules (schema, pushy-ness, overlap, coverage, MCP wiring, tool allowlist sanity).
Run the trigger evals:
```
python "${CLAUDE_PLUGIN_ROOT}/skills/ecosystem-generator/scripts/eval_triggers.py" \
  --target <output_path> --workspace <workspace_dir> --samples 10
```
This generates triggering prompts from each primitive's description and checks that the intended primitive "wins" against a baseline scorer. Results are merged into validation.json.
Read validation.json once both scripts finish.
Apply judgment on the soft signals (the scripts can't do this alone):
- Are any agent descriptions semantically redundant despite low token overlap? (e.g. "reviews code for security" vs "checks security of diffs"). If so, add a rule semantic-overlap-judgment with severity warning.
- Does the orchestration pattern actually fit the spec? (e.g. plan.md picked pipeline but sub_tasks are independent — should be orchestrator-workers). If mismatched, add rule pattern-fit-judgment with severity warning.
- Skim each generated SKILL.md for the 6 canonical sections (Purpose, When to use, Workflow, Inputs, Outputs, Examples). Missing sections → rule skill-section-completeness with severity warning.
Write final validation.json to <workspace>/validation.json with this shape:

Read the full file on GitHub · 107 lines

Changes

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.

3d ago First seen · 107 lines · 53 tokens per session scan A 8be253bd81eb

Subscribe to this mod's changes

ecosystem-validator is an agent published in the GitHub repository prgilabert/agent-ecosystem-generator (8 stars, last pushed 4mo ago), licensed MIT. It adds 53 tokens to every session and 1,267 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 2026-08-31.

Building agents agents anthropic claude-code claude-plugin mcp model-context-protocol

ecosystem-validator

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Inputs you receive

Execution protocol

What this file has done since we first saw it

Other agents, from other repositories

semble-search

design-system-architect

claude-design-orchestrator

accessibility-specialist

ci-cd-engineer

data-pipeline-engineer