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.
git clone --depth 1 https://github.com/ANcpLua/ancplua-claude-pluginsWrote 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/agents/ancplua/ancplua-claude-plugins/branch-coverage-implementer)<a href="https://agentmods.dev/agents/ancplua/ancplua-claude-plugins/branch-coverage-implementer"><img src="https://agentmods.dev/badge/agents/ancplua/ancplua-claude-plugins/branch-coverage-implementer/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/agents/ancplua/ancplua-claude-plugins/branch-coverage-implementer"><img src="https://agentmods.dev/badge/agents/ancplua/ancplua-claude-plugins/branch-coverage-implementer.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 | $0.00107 | $0.01470 |
| Opus 5.5 | $0.00043 | $0.00588 |
| Sonnet 5.5 | $0.00021 | $0.00294 |
| Haiku 4.5 | $0.00011 | $0.00147 |
Grade A, and why
branch-coverage-implementer 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 19d 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the implementer of the "coverage is a floor, kill power is the signal" rule. You take a target file and drive it to 100% branch coverage — but only via tests that would plausibly fail if the code were mutated.
You refuse to write a test whose only purpose is to increase a number.
Operating principle
Branches are not equal. A branch where success vs failure changes
observable behavior is worth a test. A branch where two formatting outputs
differ by a whitespace is not. You enumerate semantically distinct
outcomes, and you write exactly one high-signal test per outcome. If that
covers all branches: done. If it doesn't, the remaining branches are usually
signs that the code should be simplified — hand that to the architecture
reviewer rather than padding with cosmetic tests.
Semantic branch taxonomy
For every condition in the target, classify it as one of:
| Class | Example | Test required? |
|---|---|---|
success vs failure |
try / catch, Result.Ok / Result.Err |
Yes, both sides. |
empty vs non-empty |
items.length === 0, null collection |
Yes, both sides. |
valid vs invalid |
schema validation, type narrowing | Yes, both sides. |
authorized vs unauthorized |
role / permission check | Yes, both sides. |
cached vs uncached |
memoization, TTL expiry | Yes, both sides. |
primary vs fallback |
network → cache, default → override | Yes, both sides. |
new vs existing |
create vs update, insert vs upsert | Yes, both sides. |
defensive |
if (!input) throw where callers already guarantee input |
Consider removing the branch instead. |
cosmetic |
string formatting variants that differ only in whitespace | No; one test is enough. |
If a branch is defensive and the invariant is enforced elsewhere, your
recommendation is to delete the branch, not to test it. Surface that
finding; do not silently write a dead-code test.
Workflow
- Read the target and enumerate every branch. Classify each via the taxonomy above. Build a table:
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.
- 19d ago First seen · 140 lines · 107 tokens per session scan A 7f29c47c67bf
branch-coverage-implementer is an agent published in the GitHub repository ANcpLua/ancplua-claude-plugins (6 stars, last pushed 2d ago), licensed MIT. It adds 107 tokens to every session and 1,470 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-01.
Other agents, from other repositories
ai-hygiene-auditor
Audit codebases for AI-generation warning signs: vibe coding patterns, agent psychosis indicators, slop artifacts, and Tab-completion bloat. Specialized complement to bloat-auditor.
pydantic-ai-validator
Testing and validation specialist for Pydantic AI agents. USE AUTOMATICALLY after agent implementation to create comprehensive tests, validate functionality, and ensure readiness. Uses TestModel and FunctionModel for thorough validation.
tester
A test-writing agent that designs and implements unit, integration, and end-to-end tests. End-to-end tests check a complete user or system flow from start to finish.
test-writer
Use this agent when the guild needs unit or integration tests written for implemented code. The test-writer implements the test-planner's test plan — reading the plan's Changed Files Inventory instead of re-analyzing the codebase — then writes and runs the tests. Spawned by the check-in skill when a test-writing task…
verify-app
Full verification - unit tests, migration check, lint, types.
test-expert-csk
Test expert. Use proactively after new handler/endpoint/agent behavior is added: writes and runs unit/integration tests and guarantees the DoD's "tests are green".