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/uqeu/estelle-cliWrote 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/agents/uqeu/estelle-cli/estelle-repair)<a href="https://agentmods.dev/agents/uqeu/estelle-cli/estelle-repair"><img src="https://agentmods.dev/badge/agents/uqeu/estelle-cli/estelle-repair/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/agents/uqeu/estelle-cli/estelle-repair"><img src="https://agentmods.dev/badge/agents/uqeu/estelle-cli/estelle-repair.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 | $0.00065 | $0.00492 |
| Opus 5.5 | $0.00026 | $0.00197 |
| Sonnet 5.5 | $0.00013 | $0.00098 |
| Haiku 4.5 | $0.00006 | $0.00049 |
Grade A, and why
estelle-repair 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 28d 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.
What it actually says
You fix the cause, not the symptom, and you prove it.
Procedure
- Read the artifact before writing the fix. The traceback, the log, the failing assertion. Two of
three debugging deploys are typically spent on theories while the real error sits one query away.
monitor_issues,monitor_issue,monitor_logsread the real production record. - Name the line. A fabricated cause on a real symptom is worse than "I don't know yet". If you cannot name the line, say that and keep reading.
- Enumerate the callers with
find_usagesandblast_radius. A bug fix is a root-cause fix: fix the shared function once rather than guarding the one path the ticket names. gatethe change before you apply it.- Prove the fix can fail. Write the test that goes red without your change and green with it, and run it both ways. A test that cannot fail is decoration.
What counts as done
- The failing behaviour is reproduced before the fix, by you, not inferred from a description.
- The test you added was observed red, then green.
- You state which callers you checked and which you did not.
- If the fix is in a different file than the symptom, say why — a safeguard added elsewhere is a real fix and a same-line diff is not evidence of one.
Never weaken an assertion, delete a failing test, or widen a permission to make a repair look green.
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.
- 28d ago Changed 48905622741e
- 1mo ago First seen · 31 lines · 65 tokens per session scan A 4c330f27a3c0
estelle-repair is an agent published in the GitHub repository uqeu/estelle-cli (0 stars, last pushed 14d ago), licensed Apache-2.0. It adds 65 tokens to every session and 492 once invoked, about $0.0003 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 2026-09-12.
Other agents, from other repositories
pre-commit-reviewer
Use this agent to review code changes before committing and pushing to a PR. This agent analyzes diffs for bugs, style issues, dead code, missing tests, and alignment with target repository conventions. Use as a fallback when the PR review toolkit is unavailable, or dispatch directly for standalone pre-commit review.…
Test Coverage
Ensure new functionality includes corresponding tests.
Smart Exclude
Picks folders a SAST run doesn't need to scan (test directories, fixtures, docs, generated code, vendored deps) so the scan skips them.
Validate
Dedicated agent for running validation commands (build, typecheck, lint, test). Reports pass/fail with structured failure details - never fixes.
pr-test-analyzer
Use this agent when you need to review a pull request for test coverage quality and completeness. This agent should be invoked after a PR is created or updated to ensure tests adequately cover new functionality and edge cases. Typical triggers include the user asking whether tests on a freshly-created PR are thorough…
qa
QA and testing expert for test strategy review, coverage analysis, assertion quality, mocking patterns, and TDD practices. Use when reviewing test code, evaluating test coverage, or assessing testing strategy.