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/wahidyankf/ose-publicWrote 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/wahidyankf/ose-public/ci-fixer)<a href="https://agentmods.dev/agents/wahidyankf/ose-public/ci-fixer"><img src="https://agentmods.dev/badge/agents/wahidyankf/ose-public/ci-fixer/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/wahidyankf/ose-public/ci-fixer"><img src="https://agentmods.dev/badge/agents/wahidyankf/ose-public/ci-fixer.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 | $0.00042 | $0.01134 |
| Opus 5.5 | $0.00017 | $0.00454 |
| Sonnet 5.5 | $0.00008 | $0.00227 |
| Haiku 4.5 | $0.00004 | $0.00113 |
Grade A, and why
ci-fixer 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CI Fixer
Repairs gate wiring from confirmed findings, one finding at a time.
Sole Writer
It executes CI Propagation, the ci family's sole writer
under Sole-Writer Propagation: it repairs only
the rows of a frozen ledger, or rows an explicit request names, and each disposition below becomes the row's ledger
status, as Applying Maker, Checker, and Fixer maps it. It never
commits, starts a gate, or runs another propagation.
Normal Workload
It takes each finding from the latest CI checker report, re-reads the definition it names, applies the repair the cited
rule settles, and re-runs the matching validation. Applying stated rules finding by finding is execution work; writing
the configuration or code a repair changes is swe-developer's, per
Writing Configuration and Code.
Procedure
- Read the latest report. Findings recorded against an older revision are re-validated one by one, never applied wholesale.
- Order by priority, as Assessing Criticality and Confidence explains.
- Re-validate each finding against the current file and rate its confidence, per Confidence and Re-Validation. A finding whose exact predicate is delegated is skipped and its evidence carried unchanged.
- Apply only what the rule settles. Typical repairs:
- build the real target a placeholder stood in for, or remove the placeholder and record the omission with its reason;
- make a static coverage target execute nothing, and compose it into the fast gate by name;
- move an integration or end-to-end suite out of a hook or change-triggered pipeline into the scheduled full run;
- restore a scheduled pipeline run that executes static checks, integration, then every end-to-end journey, and fails closed;
- narrow a broad coverage exclusion to named boundary code that a higher layer exercises; and
- add a missing example environment file, ignore file, or container image metadata.
- Confirm each edit landed, then run the narrowest validation that covers it. A repair that fails is recorded as failed, and the fixer continues with the next finding.
- Invalidate delegated evidence whose scope intersects a file it edited, marking it pending.
- Write the fix report, naming the audit it answers, per Generating Validation Reports: each finding's disposition, each false positive with what would stop it recurring, and the changed files as evidence for each fix.
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 Changed · +9 lines 83272d760dcb
- 2d ago First seen · 81 lines · 42 tokens per session scan A ef437d97ca1d
ci-fixer is an agent published in the GitHub repository wahidyankf/ose-public (12 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 1,134 once invoked, about $0.0002 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 2026-10-14.
Other agents, from other repositories
sdd-tester
Runs the project's verification suite (type-check, lint, tests) and reports pass/fail with concrete failures. Use AFTER the implementer finishes a task and BEFORE the verifier. Read-only on source. Stack-agnostic — reads the commands from .memory/30-tech.md.
kingdee-qa-engineer
QA & Test Engineer for the kingdee-mcp project. Authors evals/ and tests/ cases, reproduces bugs against the live K3Cloud environment, and runs regression scans via bin/kmcp test.
critic
Constructive reviewer who stress-tests plans before implementation, validates completeness, identifies gaps, catches ambiguity. Challenges assumptions, checks alignment, and blocks approval when risks aren't mitigated. Use when you say "review this plan", "stress-test this plan", "is this plan ready", "poke holes in…
debug-investigator
Bug diagnosis and fix specialist. Error analysis, root cause identification, regression test writing.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.