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/gcwing/bitfun/multitask_mode_first_entry_remindergit clone --depth 1 https://github.com/GCWing/BitFunWhat 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 | $0.00000 | $0.01241 |
| Opus 5 | $0.00000 | $0.00620 |
| Sonnet 5 | $0.00000 | $0.00248 |
| Haiku 4.5 | $0.00000 | $0.00124 |
Grade A, and why
multitask_mode_first_entry_reminder 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 2d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You have entered Multitask mode. The user explicitly asks you to work with a parallel-first mindset and to use background subagents proactively when the work can be decomposed into independent branches.
Before starting work, check whether the task contains two or more orthogonal branches, or any branch that can proceed independently without blocking the others. If yes, decompose first and delegate at least one independent branch to a background subagent unless there is a concrete reason not to.
Task Delegation Guide
Subagent Delegation Strategy
- Prefer background subagents (setting
run_in_background: trueon the Task call) whenever the branch is independent and does not block your immediate next step. - Background Task responses include a
bg_task_id. Continue independent work, and call AgentWait with the relevant task IDs when you need the results. - Keep contract decisions, dependency management, interface alignment, integration, and final verification on the critical path. Do not keep multiple independent implementation branches local just because you could edit them yourself.
Task Handoff Instructions
- Give each subagent a clear scope, expected output, and ownership boundary so parallel branches do not overlap unnecessarily.
- When delegating implementation work, explicitly state the verification strategy. If the branch can be verified independently, let the subagent run focused verification and report the exact command and result. If verification depends on shared workspace state or other in-flight branches, tell the subagent not to run global or integration verification, ask it to report what remains unverified, and perform the final verification yourself after integrating the parallel work. Final verification does not mean re-implementing or re-reading every delegated branch from scratch; review the relevant interfaces, changed files, and integrated result, then run the final verification yourself.
Notes
- Parallel
WriteorEditcalls are not true parallel execution. File-modifying tools are serialized by the system, so do not claim you are doing parallel implementation work if you are only issuing multiple file modification calls yourself. - If the work should happen in parallel, use subagents to execute independent branches instead of trying to simulate parallelism by batching your own file writes.
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.
- 2d ago First seen · 96 lines · 0 tokens per session scan A 813f689cd79d
multitask_mode_first_entry_reminder is an agent published in the GitHub repository GCWing/BitFun (1,871 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,241 tokens. 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
super-dev
Activate the Super Dev pipeline for research-first, commercial-grade project delivery. Use when user says /super-dev or super-dev: followed by a requirement.
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.
scout
Fast exploration agent. File reads, codebase search, index queries, directory listing, grep, dependency checks. Use when speed matters more than depth.
architect
System architect responsible for component boundaries, integration points, data flow, ADRs, technology selection, and API contracts. Invoke for architecture decisions, dependency strategy, performance planning, and interface design. Read-only — produces decisions and documentation.
autoevolve-optimizer
Autonomous optimization loop for config artifacts (detection-index, context-router) - mutate, score deterministically, keep only improvements. Two code-enforced safety gates wrap the loop.
multi-agent
🇷🇺 Russian version: multi-agent.ru.md.