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/Ecro/harness-makerWrote 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/commands/ecro/harness-maker/make)<a href="https://agentmods.dev/commands/ecro/harness-maker/make"><img src="https://agentmods.dev/badge/commands/ecro/harness-maker/make/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/commands/ecro/harness-maker/make"><img src="https://agentmods.dev/badge/commands/ecro/harness-maker/make.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 | $0.00000 | $0.11135 |
| Opus 5.5 | $0.00000 | $0.04454 |
| Sonnet 5.5 | $0.00000 | $0.02227 |
| Haiku 4.5 | $0.00000 | $0.01114 |
Grade A, and why
make 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 9d 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 — 782 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/harness-maker:make
Refresh, reconfigure, or extend the project's harness at <cwd>/.claude/.
Asks the user what they want to do before invoking the CLI.
Procedure
You (Claude) act as the orchestrator. Follow these steps:
0. CI / test mode detection
If the prompt text contains --ci, extract inline params and skip all
AskUserQuestion calls. Parse preset=, locale=,
targets= and the optional strictness= (block / warn) from the prompt; use defaults
Side / en / claude-code for any that are absent. Export the parsed value as
$STRICTNESS (empty when absent) — every dispatch below passes
${STRICTNESS:+--strictness "$STRICTNESS"}, which forwards it when set and omits the flag
entirely when it is not, so an unset strictness leaves the preset to derive it. Likewise parse the
optional world_model_name= and world_model_handle= into $WM_NAME / $WM_HANDLE
(empty when absent); the dispatch forwards them the same way, and the CLI derives the handle
from the name — a name with no ASCII handle and no world_model_handle= exits 1 naming the
flag. Skip the live locale and world-model questions and
jump directly to section 5 (Dispatch → Fresh install or Update,
depending on whether .claude/harness.yaml exists).
Example invocation:
/harness-maker:make --ci preset=Side locale=en targets=claude-code,codex
/harness-maker:make --ci preset=Side locale=ko world_model_name=비비 world_model_handle=bibi
0.5. --reinterview shortcut
If the prompt text contains --reinterview (and is not --ci), the user
wants a full interactive reconfigure. Do not pass --reinterview through
to the CLI — the CLI's interactive interview reads from stdin, which
falls back to autoloop defaults in the slash-command context (no TTY).
Instead, skip the menu in section 3 and jump straight to the Full
reconfigure branch in section 5, which drives AskUserQuestion here in
the slash command and dispatches with collected --preset / --locale / --targets flags.
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.
- 9d ago Changed · -20 lines 36f7ed9f8b2d
- 23d ago Changed · +32 lines 9ce70acab967
- 28d ago Changed · +1 lines 74904bf42a27
- 1mo ago Changed · +4 lines 68b9c7fda8e2
- 1mo ago Changed · +4 lines 070fcf399018
- 1mo ago First seen · 761 lines · 0 tokens per session scan A fc2f6cee6996
make is a command published in the GitHub repository Ecro/harness-maker (4 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 11,135 tokens. 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.
Other commands, from other repositories
skill-registry
Rebuild the OpenCode skill registry for the current project and installed skills.
skill-creator
Create or update an OpenCode skill using the bundled skill-creator workflow.
cross-critique
Adversarial multi-angle critique. All three auditors fire in parallel (codex=technical, gemini=strategic, claude=ux). Counter-args ranked by rebuttal survival score, not raw severity. Usage: /cross-critique [--with | list | compare].
cross-audit
Second-model review. Picks an auditor (codex/gemini/opencode/aider/copilot), excludes the caller, writes a prompt to paste, reads the response back. Usage: /cross-audit [--with | list | compare].
pr-feedback-ingest
Turn PR feedback (Greptile, CI, bots, humans) into a traceable backlog, so the next step is a narrow implement-approved-slice. Corrective scope only. Use when a PR has review feedback to map to files and slices. Do not use for a new direction or contract (use post-review-pivot), no payload, or task-memory drift only…
repo-consistency-sweep
Defect-class detection for the lower-value half of code review: convention drift, type-safety gaps, security and multi-tenant invariants, operability issues. Runs after review-hard. Checks against a curated bug-class library that grows via pr-feedback-ingest. Use when at least one slice is implemented and you want a…