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 skills add Rockielab/rockie-claude --skill modegit clone --depth 1 https://github.com/Rockielab/rockie-claudeWrote 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/rockielab/rockie-claude/mode)<a href="https://agentmods.dev/skills/rockielab/rockie-claude/mode"><img src="https://agentmods.dev/badge/skills/rockielab/rockie-claude/mode/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/rockielab/rockie-claude/mode"><img src="https://agentmods.dev/badge/skills/rockielab/rockie-claude/mode.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 | $0.00118 | $0.01408 |
| Opus 5 | $0.00059 | $0.00704 |
| Sonnet 5 | $0.00024 | $0.00282 |
| Haiku 4.5 | $0.00012 | $0.00141 |
Grade A, and why
mode 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 10d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- mode — 100% identical, 16 lines differ
How it starts
The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/mode — operational overlays on the taste corpus
Identity is centralized in .rockie/taste/. Modes carry the small,
context-dependent policy bits that flip between sessions:
paper-deadline vs. exploratory vs. dogfooding vs. teaching.
A mode is a TOML file at .rockie/taste/modes/<name>.toml. The
active mode is named in .rockie/taste/modes/_active (one line).
SessionStart loads it and surfaces a compact summary alongside the
researcher identity from INDEX.md.
When to use
- A new context (deadline, area, register) where overrides apply.
- The harness behavior shouldn't change who you are, just what you optimize for this session.
Subcommands
python3 .claude/skills/mode/runtime/mode.py show # active mode + diff vs central
python3 .claude/skills/mode/runtime/mode.py list # available modes
python3 .claude/skills/mode/runtime/mode.py switch <name> # atomic flip _active
python3 .claude/skills/mode/runtime/mode.py new <name> [--from <template>]
python3 .claude/skills/mode/runtime/mode.py edit <name> # opens in $EDITOR
python3 .claude/skills/mode/runtime/mode.py diff <a> <b> # compare two modes
python3 .claude/skills/mode/runtime/mode.py active # print just the active name
Built-in templates
Shipped in <rockie>/project-harness/skills/mode/templates/. The
installer copies them into .rockie/taste/modes/ on first run if
that directory doesn't exist yet.
| Template | When |
|---|---|
default |
No overrides — central corpus is canonical |
paper-crunch |
Deadline-locked: scope_lock, formal register, smoke gates, Opus on attack/review |
exploratory |
No scope lock, broad reading window, sonnet-first, register=lab-notebook |
dogfooding |
Harness self-modification or first-run testing — tight budgets, fast cycles |
learning |
Educational sessions: register=teaching, gates relaxed, Opus on explanations |
Schema (every field optional)
name = "<slug>"
description = "<one sentence>"
[hardware]
hardware_type = "H100" | "A100" | "H200"
spot_only = true
on_demand_allowed = false
gpu_budget_dollars_per_session = 50
[reading]
focus_arxiv_categories = ["cs.LG"]
exclude_categories = ["q-bio.NC"]
recency_window_months = 6
prefer_venues = ["NeurIPS", "ICML"]
[methodology]
success_criteria_override = "<prose>"
required_ablations = ["param-matched-flat"]
allow_negative_result = true
[risk]
sanity_check_above_dollars = 10
session_max_dollars = 80
require_smoke_before_real_run = true
[output]
register = "formal-paper" | "lab-notebook" | "teaching" | "code-comment"
default_target = "<paper / blog / tinker>"
[workflow]
scope_lock = true
require_clean_before_commit = true
require_audit_subagent_before_train = true
prefer_opus_for = ["attack", "novelty-check"]
prefer_sonnet_for = ["fix-list", "research-collation"]
[dismissals]
active_categories = ["ml-architectural"] # which DISMISSALS.md tags
# are load-bearing this mode
[deadline]
target_date = "YYYY-MM-DD"
scope_lock = true
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 145 lines · 118 tokens per session scan A 300dfb1fda27
mode is a skill published in the GitHub repository Rockielab/rockie-claude (21 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 118 tokens to every session and 1,408 once invoked, about $0.0006 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 skills, from other repositories
auto-run
Autonomous personalized research loop. Use when the user wants to research a topic autonomously, run a research loop, start adaptive research, or use presets like technique-scout or cross-domain. Triggers on: 'auto run', 'research loop', 'autonomous research', 'run research', 'start research', 'adaptive research'.
autoresearch
Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports…
git-commit
A guided Git commit workflow that examines changes and creates a commit message using the Conventional Commits format, a shared style for labeling changes such as features, fixes, tests, or documentation.
pi-sync
Daily upstream-sync job for the pi Go port — fetch upstream pi, triage every change since the recorded pin, port what's in scope, verify idiomatic + parity via independent reviews, update the ledger, and push. Use for "sync with upstream", "porting job", or as the scheduled daily run.
pi-triage
Decide whether an upstream pi change needs porting to the Go port. Use when assessing upstream commits/PRs ("should we port X?"), or as the triage stage of /pi-sync. Outputs a WHY/WHAT/SCOPE verdict per change.
pi-parity-review
Adversarially verify that a ported change is faithful to the original pi implementation (TS source + published npm build). Use after porting upstream pi changes, or standalone on any area of this repo ("is X faithful to pi?").