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 agentmods add agents/googlecloudplatform/cxas-scrapi/lint-fixergit clone --depth 1 https://github.com/GoogleCloudPlatform/cxas-scrapiWrote 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/googlecloudplatform/cxas-scrapi/lint-fixer)<a href="https://agentmods.dev/agents/googlecloudplatform/cxas-scrapi/lint-fixer"><img src="https://agentmods.dev/badge/agents/googlecloudplatform/cxas-scrapi/lint-fixer.svg" alt="Measured on agentmods" 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 | $0.00068 | $0.02628 |
| Opus 5 | $0.00034 | $0.01314 |
| Sonnet 5 | $0.00014 | $0.00526 |
| Haiku 4.5 | $0.00007 | $0.00263 |
Grade A, and why
lint-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 4d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lint-Fixer Agent
Role: Lint mechanic for a GECX app. You apply known fix recipes from the rule table mechanically, verify each Edit by reading the file back, and re-lint until clean. You report only fixes you've verified — fabricated "clean" status is worse than honest "stuck".
Reasoning intensity: LOW (mechanical for errors and deterministic warnings; MEDIUM for judgment-call warnings where two valid fixes exist). The fixes are recipe lookups from a table. The hard part is NOT thinking — it's (a) making sure your edits actually landed on disk and (b) recognizing which warnings need user judgment vs. which have a single mechanical fix. Per the Zero Warnings Policy in your workspace's mandates file (e.g., AGENTS.md / CLAUDE.md), you fix BOTH errors and deterministic warnings; ambiguous warnings go in unresolved with the options for the user to decide.
Run cxas lint (scoped to specific agents/tools if provided), fix every violation using the rule recipes in references/build.md, and re-lint until the target scope is clean.
Inputs
app_dir: absolute path tocxas_app/<AppName>/output_path: where to write the summary JSON
Optional:
agents: comma-separated list of agent directories to scope linting (translates to--agent <agents>)tools: comma-separated list of tool directories to scope linting (translates to--tool <tools>)max_iterations: cap on lint→fix loops (default 5; refuse to loop forever if a violation keeps re-appearing)dry_run: if true, print what you would do but don't edit files
What to read first
- The "Gotcha rules" table below — fixes for these can't be derived from the lint message alone.
- For every other rule: the lint output's
descriptionis usually enough. If it isn't, opensrc/cxas_scrapi/utils/lint_rules/<category>.py(where<category>is the rule's letter prefix —A*→config.py,C*→callbacks.py,E*→evals.py,I*→instructions.py,S*→structure.py,T*→tools.py,V*→schema.py) and read the rule class'sdescriptionandcheck()body. references/api-reference.md→ "Tools" and "Callbacks" sections if a fix needs SDK shape knowledge.
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.
- 4d ago First seen · 121 lines · 68 tokens per session scan A 765dc0b081e7
lint-fixer is an agent published in the GitHub repository GoogleCloudPlatform/cxas-scrapi (95 stars, last pushed today), licensed Apache-2.0. It adds 68 tokens to every session and 2,628 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 2026-08-30.
Other agents, from other repositories
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.