Borrowing it
Nothing to install: this file belongs to FilipeJesus/lanes. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/FilipeJesus/lanes/main/.agents/skills/coder/SKILL.mdgit clone --depth 1 https://github.com/FilipeJesus/lanesWrote 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/filipejesus/lanes/coder)<a href="https://agentmods.dev/skills/filipejesus/lanes/coder"><img src="https://agentmods.dev/badge/skills/filipejesus/lanes/coder/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/filipejesus/lanes/coder"><img src="https://agentmods.dev/badge/skills/filipejesus/lanes/coder.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 | $0.00031 | $0.00672 |
| Opus 5.5 | $0.00012 | $0.00269 |
| Sonnet 5.5 | $0.00006 | $0.00134 |
| Haiku 4.5 | $0.00003 | $0.00067 |
Grade A, and why
coder scanned grade A with 1 finding 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 11d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
**For Git/Shell operations** (child_process, path handling, git commands): How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement Changes
Implement features and fixes across the Lanes core library, VS Code extension, and CLI.
Your Workflow
1. Understand the Task
- Read relevant files to understand the current implementation
- Identify which files need to be modified
2. Plan Tests First (MANDATORY)
Before writing ANY code, plan what tests are needed and document them in tests.json:
{
"planned": [
{
"id": "test-id",
"description": "What the test verifies",
"file": "src/test/session/session-provider.test.ts",
"suite": "Suite name",
"priority": "critical|high|medium|low",
"acceptance_criteria": ["Given X, when Y, then Z"],
"implemented": false
}
]
}
Rules for tests.json:
- Create it before writing any implementation code
- Include acceptance criteria for each test
- Set priority (critical tests first)
- All tests start with
implemented: false - Delete the file when the task is complete
3. Implement Changes
After planning tests:
- Make the necessary code changes using the client's file editing tools
- Follow existing code patterns and style
4. Verify with Specialists
For VS Code API logic (src/vscode/, package.json, TreeDataProvider, commands):
- Apply the vscode-expert skill
- Review API correctness, manifest integrity, and proper disposable registration
For Git/Shell operations (child_process, path handling, git commands):
- Apply the shell-ops skill
- Verify path safety, proper quoting, and error handling
If the client supports sub-agents, these reviews can be delegated with the relevant skill instructions. Otherwise, perform the same checks directly.
5. Hand Off to Test Engineer
After implementation:
- Apply the test-engineer skill, directly or through delegation
- Read
tests.jsonand implement the planned tests
Key Files in This Project
src/core/- Platform-independent business logic and code agent implementationssrc/vscode/extension.ts- Main extension entry pointsrc/vscode/commands/andsrc/vscode/services/- Commands and terminal managementsrc/vscode/providers/AgentSessionProvider.ts- Tree data provider for sidebarsrc/cli/- Standalone CLI and platform adapterspackage.json- Extension manifest (commands, views, menus)src/test/- Tests mirroring the source structure
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.
- 11d ago First seen · 85 lines · 31 tokens per session scan A 5f470c820fcd
coder is a skill published in the GitHub repository FilipeJesus/lanes (11 stars, last pushed 11d ago), licensed MIT. It adds 31 tokens to every session and 672 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-19.
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".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
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.