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 GregoryHo/arcforge --skill tddgit clone --depth 1 https://github.com/GregoryHo/arcforgeWrote 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/gregoryho/arcforge/tdd)<a href="https://agentmods.dev/skills/gregoryho/arcforge/tdd"><img src="https://agentmods.dev/badge/skills/gregoryho/arcforge/tdd/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/gregoryho/arcforge/tdd"><img src="https://agentmods.dev/badge/skills/gregoryho/arcforge/tdd.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 | $0.00036 | $0.01375 |
| Opus 5.5 | $0.00014 | $0.00550 |
| Sonnet 5.5 | $0.00007 | $0.00275 |
| Haiku 4.5 | $0.00004 | $0.00137 |
Grade A, and why
tdd 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 today.
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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test-Driven Development
The Iron Law
NO PRODUCTION CODE WITHOUT A FAILING TEST FIRST
Production code written before its test is deleted, not kept. Delete means delete: not kept as a reference, not adapted while the test is written, not read one more time. Code you did not reconstruct from a failing test is untested code wearing a passing suite — the suite was written to fit what the code already does.
The law covers new features, bug fixes, and any change to existing behavior. The only exemptions are throwaway prototypes, generated code, and configuration, and each one requires the user to approve it out loud before you skip the cycle.
The cycle
Each step names what has to be true before the next one starts.
1. Find a reference. Look for a similar implementation already in this codebase before designing a new one. Done when: you have named the closest existing implementation, or established that none exists.
2. RED — write one failing test. One behavior per test. The name states the behavior, not the function. Exercise real code; mock only what cannot run inside a test. Done when: the test file exists and asserts a behavior no code implements yet.
3. Verify RED — run it and read the failure. Never skip this. A test you did not watch fail is a test you cannot trust. Done when: the run reports a failure (not an error) whose message names the missing behavior. It passed → it asserts behavior that already exists; rewrite it. It errored → fix the error and rerun until it fails for the intended reason.
4. GREEN — the smallest code that passes. No extra parameters, no adjacent cleanups, no capability the test does not demand. Done when: the target test passes, every other test still passes, and the output carries no new warnings.
5. REFACTOR — clean up while green. Remove duplication, improve names, extract helpers. Done when: the test results are unchanged and no behavior was added.
Then return to step 2 with the next behavior.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today First seen · 131 lines · 36 tokens per session scan A 1e6812e5084d
tdd is a skill published in the GitHub repository GregoryHo/arcforge (8 stars, last pushed 12d ago), licensed MIT. It adds 36 tokens to every session and 1,375 once invoked, about $0.0001 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 2026-11-07.
tdd compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| tddGregoryHo/arcforge | Skill | 8 | 12d ago | MIT | A | 36 | Claude Code, Codex |
| systematic-debuggingopen-metadata/OpenMetadata | Skill | 16k | yesterday | Apache-2.0 | A | 37 | Claude Code |
| log-error-digestzebbern/claude-code-guide | Skill | 4.7k | 3d ago | MIT | A | 71 | Claude Code, Codex |
| cwv-optimizeradobe/skills | Skill | 319 | yesterday | Apache-2.0 | A | 112 | Claude Code |
| ci-fixersipyourdrink-ltd/bernstein | Skill | 1.2k | yesterday | Apache-2.0 | A | 15 | Claude Code, Codex |
| incident-response-incident-responsermyndharis/antigravity-skills | Skill | 1.9k | 23d ago | MIT | A | 36 | Claude Code |
| triaging-web-analytics-supportPostHog/posthog | Skill | 41k | yesterday | none | A | 151 | Claude Code, Codex |