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 summarybotng/summarybot-ng --skill qe-iterative-loopgit clone --depth 1 https://github.com/summarybotng/summarybot-ngWrote 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/summarybotng/summarybot-ng/qe-iterative-loop)<a href="https://agentmods.dev/skills/summarybotng/summarybot-ng/qe-iterative-loop"><img src="https://agentmods.dev/badge/skills/summarybotng/summarybot-ng/qe-iterative-loop/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/summarybotng/summarybot-ng/qe-iterative-loop"><img src="https://agentmods.dev/badge/skills/summarybotng/summarybot-ng/qe-iterative-loop.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 | $0.00060 | $0.03267 |
| Opus 5 | $0.00030 | $0.01633 |
| Sonnet 5 | $0.00012 | $0.00653 |
| Haiku 4.5 | $0.00006 | $0.00327 |
Grade A, and why
QE Iterative Loop 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 5d 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 — 446 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QE Iterative Loop
Overview
QE Iterative Loop is a specialized adaptation of the Ralph Wiggum technique for Quality Engineering workflows. It enables autonomous, self-correcting quality cycles where AI agents iterate until quality objectives are achieved - tests pass, coverage targets met, quality gates satisfied, or flaky tests stabilized.
Why QE Benefits from Iteration
Quality Engineering has objective, measurable success criteria:
- Tests either pass or fail (exit code 0 vs non-zero)
- Coverage is quantifiable (78.5% vs 80% target)
- Quality gates have binary outcomes (pass/fail)
- Contract validation has clear schemas
This makes QE ideal for iterative loops - we know exactly when we're done.
Prerequisites
- AQE v3 fleet initialized
- Test framework configured (Jest, Vitest, Pytest, etc.)
- Coverage tooling (c8, istanbul, coverage.py)
- Quality gate definitions
Quick Start
Pattern 1: Test Fix Iteration
# Task: Fix all failing tests
/qe-loop "Run npm test and fix all failing tests.
Success: npm test exits with code 0
Output <promise>TESTS_GREEN</promise> when all tests pass."
Pattern 2: Coverage Target Iteration
# Task: Achieve 80% coverage
/qe-loop "Increase test coverage to 80%.
Success: Coverage report shows >= 80%
Output <promise>COVERAGE_MET</promise> when target achieved."
Pattern 3: Quality Gate Iteration
# Task: Pass all quality gates
/qe-loop "Pass all quality gates for deployment.
Gates:
- Unit tests: pass
- Integration tests: pass
- Coverage: >= 80%
- No critical vulnerabilities
- Performance < 200ms P95
Output <promise>QUALITY_GATES_PASSED</promise> when all pass."
QE Iteration Patterns
Pattern 1: Test-Fix Iteration Loop
Goal: All tests pass
## QE Test-Fix Loop
### Success Criteria
- `npm test` (or test command) returns exit code 0
- No skipped tests (unless explicitly allowed)
- No pending tests
### Iteration Steps
1. Run full test suite
2. Parse output for failures
3. Analyze first failure:
- Identify failing test file
- Understand assertion that failed
- Check if production code or test is wrong
4. Fix the issue
5. Re-run failed test file only (faster feedback)
6. If file passes, run full suite
7. If all pass -> output <promise>TESTS_GREEN</promise>
8. If failures remain -> continue to next failure
### Safety
- Max iterations: 30
- After 10 iterations: report remaining failures
- Stop if same test fails 5 times (possible design issue)
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.
- 5d ago First seen · 446 lines · 60 tokens per session scan A 279026a30e36
QE Iterative Loop is a skill published in the GitHub repository summarybotng/summarybot-ng (2 stars, last pushed 3mo ago), licensed MIT. It adds 60 tokens to every session and 3,267 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.