test-gap

test-gap is a command for coding agents from atuljha23/holocron. It costs 35 tokens per session (342 once invoked), scanned A, original, MIT.

A command that reviews source code and its tests to find branches and unusual cases that tests do not cover. A branch is a possible path through the code, such as an error condition.

In plain words
What is it for?
Use it on a file or code change to get a prioritised list of missing test cases, proposed test names, and the checks each test should make.
Why use it?
It identifies specific untested situations that could hide regressions instead of giving the vague advice to write more tests.

Command

Part of the holocron plugin — 11 skills, 24 commands, 14 agents, 6 hooks shipped together

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 commands/atuljha23/holocron/test-gap
Clone the repo
git clone --depth 1 https://github.com/atuljha23/holocron

Or install holocron, the plugin that ships this one along with the rest of its 11 skills, 24 commands, 14 agents, 6 hooks.

Wrote 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.

agentmods badge for test-gap

README.md
[![agentmods](https://agentmods.dev/badge/commands/atuljha23/holocron/test-gap.svg)](https://agentmods.dev/commands/atuljha23/holocron/test-gap)
Your own site
<a href="https://agentmods.dev/commands/atuljha23/holocron/test-gap"><img src="https://agentmods.dev/badge/commands/atuljha23/holocron/test-gap.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 342 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 $0.00035 $0.00342
Opus 5 $0.00017 $0.00171
Sonnet 5 $0.00007 $0.00068
Haiku 4.5 $0.00003 $0.00034

Measured 4d ago against content hash 7114d3eafafd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test-gap 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 4d 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.

commands/test-gap.md · 40 lines

What it actually says

/holocron:test-gap

Target: $ARGUMENTS — or the changed files if no arg.

Gather

  • The target source file(s)
  • The matching test file(s) — convention: foo.tsfoo.test.ts / foo.spec.ts / test_foo.py / foo_test.go
  • For each source file, list the public API surface (exports, classes, functions)

Delegate

Spawn @qa-engineer and ask for:

  • Gaps — branches / conditions / edge cases not currently exercised by tests. Not a line-coverage number. Name the cases.
  • Priority — which gaps are most likely to hide a real regression.
  • Draft tests — for each top gap, a test name and a 2-line assertion sketch.

Output format

## Gap 1 — <short name>  [priority: high]
- Not tested: <the specific condition>
- Risk: <what breaks in prod>
- Draft test:
  - name: "<it should …>"
  - assert: <the check, concretely>

Do not

  • Do not say "add more tests" without naming the case.
  • Do not propose tests that mirror the implementation (they protect nothing).
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. 4d ago First seen · 40 lines · 35 tokens per session scan A 7114d3eafafd

Subscribe to this mod's changes

test-gap is a command published in the GitHub repository atuljha23/holocron (2 stars, last pushed 4mo ago), licensed MIT. It adds 35 tokens to every session and 342 once invoked, about $0.0002 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.