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 bjorn-ingmanson/thefroject-plugins --skill maker-checkergit clone --depth 1 https://github.com/bjorn-ingmanson/thefroject-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/skills/bjorn-ingmanson/thefroject-plugins/maker-checker)<a href="https://agentmods.dev/skills/bjorn-ingmanson/thefroject-plugins/maker-checker"><img src="https://agentmods.dev/badge/skills/bjorn-ingmanson/thefroject-plugins/maker-checker/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/bjorn-ingmanson/thefroject-plugins/maker-checker"><img src="https://agentmods.dev/badge/skills/bjorn-ingmanson/thefroject-plugins/maker-checker.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 | $0.00046 | $0.00608 |
| Opus 5 | $0.00023 | $0.00304 |
| Sonnet 5 | $0.00009 | $0.00122 |
| Haiku 4.5 | $0.00005 | $0.00061 |
Grade A, and why
maker-checker 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 8d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maker-Checker
Separate creation from validation. One agent builds, another checks. They loop until the output passes.
When to Use This Pattern
- Output quality matters and self-review is not enough
- You have clear acceptance criteria that can be checked independently
- The creator should focus on building, not second-guessing
Process
Phase 1: Define Acceptance Criteria
Before any work starts, write down what "done" looks like:
- What must the output contain?
- What must it NOT contain?
- What quality bar must it meet? (compiles, passes tests, follows conventions, reads clearly)
- Maximum iterations before escalating to the user (default: 3)
Phase 2: Make
Spawn the Maker agent with:
- The full task description
- All relevant context
- The acceptance criteria (so it knows what the Checker will look for)
- Write and edit tools as needed
The Maker produces the first version.
Phase 3: Check
Spawn the Checker agent with:
- The Maker's output
- The acceptance criteria
- Read-only tools (the Checker never modifies the output directly)
The Checker returns one of:
- PASS: Output meets all criteria. Include a brief summary of what was verified.
- FAIL: Output does not meet criteria. List specific issues with line references.
Phase 4: Loop or Deliver
If PASS: deliver the output. Done.
If FAIL: send the Checker's feedback back to the Maker as a new agent call. The Maker revises and resubmits. Repeat until PASS or max iterations.
If max iterations reached: present both the latest output and the remaining issues to the user for a decision.
Example
Task: "Write a database migration to add user preferences"
Round 1:
- Maker writes the migration
- Checker reviews: "FAIL. Missing rollback function. No index on user_id foreign key."
Round 2:
- Maker revises with Checker's feedback
- Checker reviews: "PASS. Migration includes up/down, indexes, and matches existing naming conventions."
Rules
- The Checker never edits the output. It only judges.
- The Maker receives the Checker's full feedback, not a summary. Specifics drive better revisions.
- Cap at 3 iterations. If 3 rounds of feedback cannot fix it, the task needs rethinking, not more loops.
- Keep the Checker's tool set minimal. Read and Grep only. Independence is the point.
- The acceptance criteria must be written before the first Make. Do not add new criteria mid-loop.
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.
- 8d ago First seen · 80 lines · 46 tokens per session scan A 91c63a00f2d2
maker-checker is a skill published in the GitHub repository bjorn-ingmanson/thefroject-plugins (1 stars, last pushed 2mo ago), licensed MIT. It adds 46 tokens to every session and 608 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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…