A command for adding a sanitized test fixture when a statusline payload has a new data shape or failure case. A fixture is saved sample input used to test parsing behavior.

Adding payload samples, updating parser and command-line tests, and checking that invalid values become safe nulls and valid results match the schema.

It helps ensure unusual or broken inputs are handled safely and do not crash the program, while valid fields continue to work.

How tyejcoleman/tokenroom configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to tyejcoleman/tokenroom. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/tyejcoleman/tokenroom/main/.claude/commands/add-fixture.md

Clone the repo

git clone --depth 1 https://github.com/tyejcoleman/tokenroom

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/tyejcoleman/tokenroom/add-fixture.svg)](https://agentmods.dev/commands/tyejcoleman/tokenroom/add-fixture)

Your own site

<a href="https://agentmods.dev/commands/tyejcoleman/tokenroom/add-fixture"><img src="https://agentmods.dev/badge/commands/tyejcoleman/tokenroom/add-fixture.svg" alt="Measured on agentmods" height="20"></a>

Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 295 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00016	$0.00295
Opus 5	$0.00008	$0.00148
Sonnet 5	$0.00003	$0.00059
Haiku 4.5	$0.00002	$0.00030

Measured 6d ago against content hash 7c0cda15bb6c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

add-fixture 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 6d 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.

.claude/commands/add-fixture.md · 21 lines

What it actually says

Add a payload fixture for: $ARGUMENTS

The fixture corpus (test/fixtures/) is the foundation of ADR-5 (degrade, never crash). Every payload shape observed in the wild — especially broken ones — becomes a fixture.

Sanitize the payload: replace session_id, paths, and any identifying values with synthetic ones; keep the structural anomaly byte-faithful (that's the point).
Save as test/fixtures/statusline-<short-name>.json with a name describing the shape (e.g. statusline-epoch-leak.json, not statusline-bug3.json).
Add assertions to test/state.test.mjs: what parsePayload must produce — bad fields become null (never crash, never out-of-range), good fields survive, and the result validates against the schema (validateResourceState → []).
If the tap/hook surface behavior changes (HUD/stamp text), cover it in test/cli.test.mjs.
npm test green; mention the fixture in the PR with where/how the payload was observed (Claude Code version, plan, model).

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.

6d ago First seen · 21 lines · 16 tokens per session scan A 7c0cda15bb6c

Subscribe to this mod's changes

add-fixture is a command published in the GitHub repository tyejcoleman/tokenroom (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 16 tokens to every session and 295 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 2026-08-31.

Claude Code Testing ai-agents claude context-window developer-tools mcp

tokenroom: Command for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other commands, from other repositories

ijfw-audit

api-aqa-flow-execution-and-report-analysis

ng-red-team

fire-verify-uat

generate-tests

dream