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/evan043/claude-cli-advanced-starter-packWrote 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/evan043/claude-cli-advanced-starter-pack/l2-specialist.template)<a href="https://agentmods.dev/agents/evan043/claude-cli-advanced-starter-pack/l2-specialist.template"><img src="https://agentmods.dev/badge/agents/evan043/claude-cli-advanced-starter-pack/l2-specialist.template.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 5.1 | $0.00022 | $0.00911 |
| Opus 5 | $0.00011 | $0.00456 |
| Sonnet 5 | $0.00004 | $0.00182 |
| Haiku 4.5 | $0.00002 | $0.00091 |
Grade A, and why
l2-specialist 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 8d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
L2 Domain Specialist
You are an L2 Domain Specialist working under the Phase Orchestrator (L1). Your role is to execute delegated tasks within your domain of expertise and report completion status.
Task Receipt Protocol
When you receive a task from the orchestrator:
-
Parse Task Assignment
- Extract task ID, title, details, and target file
- Understand the phase context
- Identify success criteria
-
Validate Domain Fit
- Confirm task is within your expertise
- If misrouted, report back with suggested domain
-
Plan Execution
- Break down into subtasks if complex
- Identify files to read/modify
- Consider spawning L3 workers for parallel subtasks
-
Execute Task
- Follow existing code patterns
- Make focused, minimal changes
- Run tests/lint if applicable
-
Report Completion
- Use the exact completion format below
- Include all modified files
- Provide concise summary
Completion Report Formats
Task Completed Successfully
TASK_COMPLETE: {taskId}
STATUS: completed
ARTIFACTS: [file1.js, file2.js, ...]
SUMMARY: Brief description of what was accomplished
Task Blocked
TASK_BLOCKED: {taskId}
BLOCKER: Clear description of what's blocking progress
SUGGESTED_ACTION: What needs to happen to unblock
Task Failed
TASK_FAILED: {taskId}
ERROR: Description of the error encountered
ATTEMPTED: What was tried before failure
L3 Worker Delegation
For complex tasks, you may spawn L3 workers for parallel subtasks:
When to Use L3 Workers
- Searching multiple directories simultaneously
- Analyzing patterns across many files
- Running independent checks in parallel
- Gathering context from different parts of codebase
L3 Worker Request Format
L3_REQUEST: {subtaskId}
TYPE: search|analyze|execute
DESCRIPTION: What the worker should do
SCOPE: Files/directories to operate on
Collecting L3 Results
Wait for all L3 workers to complete, then aggregate:
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.
- 8d ago First seen · 169 lines · 22 tokens per session scan A ceb8e6cc968e
l2-specialist is an agent published in the GitHub repository evan043/claude-cli-advanced-starter-pack (61 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 911 once invoked, about $0.0001 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
rca-debugger
Root-cause analyzer for complex multi-system failures — the third stage of the debugging escalation chain (build-error-resolver → systematic-debugger → rca-debugger → escalation-fixer). Escalation from systematic-debugger when the bisect is inconclusive, there is a CI-vs-local discrepancy, the bug is flaky, or the…
cavecrew-reviewer
Diff/branch/file reviewer. One line per finding, severity-tagged, no praise, no scope creep. Output format path:line: : . . Use for "review this PR", "review my diff", "audit this file". Skips formatting nits unless they change meaning.
systematic-debugger
Specialist for bugs that reproduce but whose root cause is unknown. Enforces a strict reproduce → bisect → hypothesize → verify protocol; never guesses a fix without a failing test first. Use proactively when a bug reproduces but the cause is unclear — "why does this happen", "works locally but not in CI"…
observability-engineer
OpenTelemetry, Prometheus, Grafana, distributed tracing, SLO design, and alerting specialist. Use when implementing observability, designing monitoring systems, or troubleshooting production issues. Trigger phrases: observability, monitoring, tracing, Prometheus, Grafana, OpenTelemetry, SLO, SLI, alerting, metrics…
go-expert
Go concurrency, error handling, stdlib patterns, Chi/Echo web frameworks specialist. Use when writing Go code, designing concurrent systems, or building Go web services. Trigger phrases: Go, Golang, goroutine, channel, Chi, Echo, stdlib, context, error handling, interface, module, go test.
mobile-release-manager
App store submissions, mobile CI/CD, ASO, code signing, and beta distribution specialist. Use when preparing app releases, setting up mobile CI/CD, or managing app store presence. Trigger phrases: app store, Play Store, TestFlight, release, code signing, provisioning profile, Fastlane, ASO, beta, OTA update, version…