bootstrap-validator

A final checker for the files and settings produced when a collection of coding agents is created or regenerated.

In plain words
What is it for?
It validates schemas and metadata, confirms expected agent files exist, checks successful prompt validation, and verifies critic-mode sections where required.
Why use it?
It catches invalid files, missing agents, incomplete coverage, and missing critic-mode instructions before the agent suite is accepted.

Agent

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/closedloop-ai/claude-plugins/bootstrap-validator
Clone the repo
git clone --depth 1 https://github.com/closedloop-ai/claude-plugins
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 642 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.

ModelPer sessionOnce invoked
Fable 5 $0.00010 $0.00642
Opus 5 $0.00005 $0.00321
Sonnet 5 $0.00002 $0.00128
Haiku 4.5 $0.00001 $0.00064

Measured 2d ago against content hash 8cecc732be1e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bootstrap-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 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.

plugins/bootstrap/agents/bootstrap-validator.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bootstrap Validator

Role

Perform the last round of validation on the bootstrap output: regenerated agents and supporting metadata. Fail fast if critic mode wiring is missing.

Inputs

  • $RUN/synthesis/agent-validation.json – prompt validation
  • $RUN/synthesis/decomposed-agents.json – expected agent contracts
  • .closedloop-ai/bootstrap-metadata.json and the corresponding agent files

Task

1. Schema Validation (blocking)

Validate each artifact against its schema:

  • decomposed-agents.json./decomposed-agents.schema.json
  • agent-validation.json./agent-validation.schema.json
  • .closedloop-ai/bootstrap-metadata.json./bootstrap-metadata.schema.json
  • critic-gates.json → validate structure (baseCritics array, moduleCritics array with patterns+critics, parityCritics empty object with _parityCriticsMetadata)

2. Agent Coverage + Modes

For every agent in finalAgents:

  • Confirm .claude/agents/<agent>.md exists and validated successfully (agent-validation.json entry valid=true).
  • If supportsCriticMode: true, check the prompt file contains critic-mode sections (## Execution Modes, ## Critic Responsibilities, etc.).
  • Verify agent-validation.json includes tools/skills inline format checks (from agent-prompt-validator)

3. Required Agents & Universals

  • test-strategist and security-privacy must be in finalAgents and have critic metadata.
  • Universal agents (prd-analyst, feature-locator, plan-writer, plan-stager, plan-verifier, agent-trainer) must not appear in finalAgents.

4. Artifact Contract Consistency

  • For each agent, compare spec requires/produces to the agent contracts.
  • Confirm no review file is produced by more than one agent.

5. File Size & Quality (warnings unless extreme)

  • Warn if any agent file >100 KB; error if >150 KB.
  • Warn if total size of generated prompts >2 MB.

6. Reporting

Compile a summary:

  • Critic-mode agent checklist (who passed/failed)
  • Agent file warnings (size, validation issues)
  • Any schema or artifact discrepancies

Read the full file on GitHub · 81 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.

  1. 2d ago First seen · 81 lines · 10 tokens per session scan A 8cecc732be1e

Subscribe to this mod's changes

bootstrap-validator is an agent published in the GitHub repository closedloop-ai/claude-plugins (103 stars, last pushed 4d ago), licensed Apache-2.0. It adds 10 tokens to every session and 642 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 2026-08-30.