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 QBall-Inc/the-bulwark --skill bulwark-verifygit clone --depth 1 https://github.com/QBall-Inc/the-bulwarkWrote 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/qball-inc/the-bulwark/bulwark-verify)<a href="https://agentmods.dev/skills/qball-inc/the-bulwark/bulwark-verify"><img src="https://agentmods.dev/badge/skills/qball-inc/the-bulwark/bulwark-verify/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/qball-inc/the-bulwark/bulwark-verify"><img src="https://agentmods.dev/badge/skills/qball-inc/the-bulwark/bulwark-verify.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 | $0.00028 | $0.03927 |
| Opus 5 | $0.00014 | $0.01963 |
| Sonnet 5 | $0.00006 | $0.00785 |
| Haiku 4.5 | $0.00003 | $0.00393 |
Grade C, and why
bulwark-verify scanned grade C with 2 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 11d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Manual cleanup: `rm -rf tmp/verification/*` Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- Has `spawn`/`exec`/`execSync` imports → Process Spawner How it starts
The opening of the file, as written. The whole thing — 542 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bulwark Verify
Purpose
Generate runnable verification scripts that test real component behavior without mocks. This skill orchestrates assertion-patterns (P2.1) and component-patterns (P2.2) to produce executable scripts for any component type.
When to Use
Load this skill when:
- User requests
/bulwark-verify [path] - test-audit Step 7 needs verification scripts
- Generating standalone verification for a component
DO NOT use for:
- Running existing tests (use
just test) - Writing unit tests (implement directly)
- Test auditing (use
test-auditskill)
Usage
/bulwark-verify [path] [--execute]
Examples:
/bulwark-verify src/cli.ts- Generate verification script for CLI/bulwark-verify src/server.ts --execute- Generate and run/bulwark-verify- Infer from recent context
MANDATORY EXECUTION STEPS
WARNING: These steps are BINDING instructions, not suggestions. You MUST execute each step in order. Do NOT substitute your judgment for these instructions. Do NOT skip sub-agent spawning. Do NOT modify the execution flow.
When this skill is loaded, execute these steps exactly as written:
Step 1: Resolve Target
IF $ARGUMENTS provided:
target = first non-flag argument
execute_flag = "--execute" in $ARGUMENTS
ELSE:
Look for component files in recent conversation context
IF found: target = that path
ELSE: Ask user: "Which component should I generate a verification script for?"
Step 2: Detect Project Language
Check for project manifest files in order (search from target file's directory up to project root):
| Check | Language | Test Runner |
|---|---|---|
package.json exists |
Node | jest/vitest/node |
pyproject.toml OR setup.py exists |
Python | pytest/python |
Cargo.toml exists |
Rust | cargo test |
| None of the above | Generic | bash |
Step 3: Analyze Component
-
Read the target file
-
Identify component type using indicators from
component-patternsskill:- Has
spawn/exec/execSyncimports → Process Spawner - Has
listen()/createServer/express()/fastify()→ HTTP Server - Has
fs.readFile/parsefunctions → File Parser - Has
process.argv/yargs/commander/argparse→ CLI Command - Has database imports (
pg,mysql,mongoose,prisma) → Database - Has
fetch/axios/got/requestscalls → External API
- Has
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.
- 11d ago First seen · 542 lines · 28 tokens per session scan C 22be6792c23d
bulwark-verify is a skill published in the GitHub repository QBall-Inc/the-bulwark (8 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 3,927 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
journey-simulation
Use when caller wants to observe how a stranger encounters a flow, artifact, or sandbox — triggers like "simulate a user journey", "test our onboarding / checkout / signup", "will my ICP convert", "how does a cold reader experience this README", "first-time user test", "cognitive walkthrough", or any request to…
black-box-test
Use as an INDEPENDENT tester agent to test another agent's intesting ticket from the OUTSIDE — never your own, and never from the implementation diff. You test from the operational test contract + acceptance criteria only (never HOW it was built), writing automated tests that invoke the changed surfaces and recording…
java-conventions
Use when a ticket adds or changes Java code and it must follow the repo's Java conventions — modern Java (records, sealed types, pattern matching, switch expressions), Optional discipline, immutability, Spring Boot constructor injection, and JUnit 5 + Mockito tests. Invoke for "add this in Java", "fix the Java build"…
python-conventions
Use when a ticket adds or changes Python code and it must follow the repo's Python conventions — PEP 8, full type hints, dataclasses, pythonic idioms, explicit error handling, and pytest with coverage. Invoke for "add this in Python", "fix the type/lint errors", "add the FastAPI/Django endpoint", or as the language…
add-integration-test
Use when a ticket asks for integration or end-to-end coverage across components — an API route hitting a database, a service-to-service call, a multi-step flow — rather than a single unit. Invoke for "test the endpoint end to end", "cover the checkout flow", or "verify the migration + query together".
record-evidence
Use after implementing a Dispatch ticket and running its checks, to produce and record acceptance-criterion evidence, then STOP. Invoke whenever you have finished and committed work on your claimed ticket and need to evidence each AC. Recording evidence is where your job ENDS — the runner (not you) records the…