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/vkirill/claude-lane-stack/codex-onboardergit clone --depth 1 https://github.com/VKirill/claude-lane-stackWrote 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/vkirill/claude-lane-stack/codex-onboarder)<a href="https://agentmods.dev/agents/vkirill/claude-lane-stack/codex-onboarder"><img src="https://agentmods.dev/badge/agents/vkirill/claude-lane-stack/codex-onboarder.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 | $0.00033 | $0.00890 |
| Opus 5 | $0.00016 | $0.00445 |
| Sonnet 5 | $0.00007 | $0.00178 |
| Haiku 4.5 | $0.00003 | $0.00089 |
Grade A, and why
codex-onboarder scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
codex-onboarder → project-onboarder (compat alias)
Deprecated name. Prefer
project-onboarder. This agent is identical for one release cycle.
project-onboarder (canonical conveyor role)
Function name, not the adoc daytime writer. Implementation shell-out may be Codex CLI. Compatibility alias still installed:
codex-onboarder.
Model + effort (token-aware)
| Depth | Codex model | Effort |
|---|---|---|
| minimal | gpt-5.6-terra |
medium |
| deep (default when scenario=full) | gpt-5.6-sol |
high |
No 5.5 / Luna. No default xhigh. No "fast" write lane.
See docs/decisions/ADR-codex-effort.md.
Inputs
PROJECT_CWD, optional ARTIFACT_DIR, FORCE, CODEX_MODEL, CODEX_REASONING,
ONBOARD_SCENARIO=minimal|full, ONBOARD_DEPTH=minimal|deep
Run
- Instructions:
~/.agents/codex/instructions/onboard.md - Seed + detect:
export PATH="$HOME/.agents/bin:$PATH"
cd "$PROJECT_CWD"
mkdir -p "${ARTIFACT_DIR:-$PROJECT_CWD/.agents/runs/_onboard/artifacts/001}"
ARGS=()
[[ -n "${ONBOARD_SCENARIO:-}" ]] && ARGS+=(--"$ONBOARD_SCENARIO")
# map legacy ONBOARD_DEPTH=fast → minimal
if [[ "${ONBOARD_DEPTH:-}" == "fast" ]]; then ONBOARD_DEPTH=minimal; fi
[[ -n "${ONBOARD_DEPTH:-}" ]] && ARGS+=(--"$ONBOARD_DEPTH")
project-onboard "$PROJECT_CWD" "${ARGS[@]}"
agents-doctor --apply "$PROJECT_CWD" 2>/dev/null || true
# Read .agents/onboard.scenario.yaml → depth
# Read ARTIFACT_DIR/deep-scan.md
- Choose model + effort from depth (unless env override).
- Run Codex following onboard.md checklist for that depth.
- Prefer timeout ≥ 900s for deep, ≥ 600s for minimal.
CODEX_MODEL="${CODEX_MODEL:-}"
CODEX_REASONING="${CODEX_REASONING:-}"
DEPTH=$(awk '/^depth:/{print $2}' .agents/onboard.scenario.yaml 2>/dev/null || echo deep)
[[ "$DEPTH" == "fast" ]] && DEPTH=minimal
if [[ -z "$CODEX_MODEL" ]]; then
if [[ "$DEPTH" == "deep" ]]; then CODEX_MODEL=gpt-5.6-sol; else CODEX_MODEL=gpt-5.6-terra; fi
fi
if [[ -z "$CODEX_REASONING" ]]; then
if [[ "$DEPTH" == "deep" ]]; then CODEX_REASONING=high; else CODEX_REASONING=medium; fi
fi
# codex exec --model "$CODEX_MODEL" -c model_reasoning_effort="$CODEX_REASONING" ... < SPEC
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 675cfcfffdfd
- 5d ago First seen · 87 lines · 33 tokens per session scan A b4fcd8285d5d
codex-onboarder is an agent published in the GitHub repository VKirill/claude-lane-stack (114 stars, last pushed 3d ago), licensed MIT. It adds 33 tokens to every session and 890 once invoked, about $0.0002 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
system-architect
Use this agent when making architectural decisions for RTK — adding new filter modules, evaluating command routing changes, designing cross-cutting features (config, tracking, tee), or assessing performance impact of structural changes. Examples: designing a new filter family, evaluating TOML DSL extensions, planning…
ERROR-FIX
A model-mediated harness for reliable agentic software development.
code-reviewer
Use for thorough code review with quality, security, and performance checks.
integration-reviewer
Runtime integration validator — read-only. Validates service connection parameters, async/sync consistency, env var completeness, library API correctness, and OTEL pipeline completeness. Triggered during /plan-validate when new services, libraries, or observability config are in scope.
loop-monitor
Autonomous loop monitor — detects stalls, token runaway, and infinite loops in long-running unattended Claude sessions. Use alongside a watchdog process when running autonomous pipelines.
output-evaluator
Evaluate Claude Code outputs for quality before commit/action (LLM-as-a-Judge pattern).