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/juspay/neurolink/task-checklistgit clone --depth 1 https://github.com/juspay/neurolinkWhat 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 | $0.01224 |
| Opus 5 | $0.00000 | $0.00612 |
| Sonnet 5 | $0.00000 | $0.00245 |
| Haiku 4.5 | $0.00000 | $0.00122 |
Grade A, and why
TASK-CHECKLIST 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Checklist (tasks_create / tasks_update / tasks_list)
A long-running agent that plans in prose loses the plan the moment the conversation is summarized. The task checklist keeps the plan out of the message list: it is session state the model edits through three tools and the host reads synchronously — so "did this run actually finish everything?" is a question code can answer, with no LLM in the loop.
Opt-in and additive: nothing registers these tools until you ask.
Quick start
import { NeuroLink } from "@juspay/neurolink";
const neurolink = new NeuroLink();
neurolink.registerTaskTools();
neurolink.setToolContext({ sessionId: "review-1421" }); // gives the checklist an identity
await neurolink.generate({
input: {
text: "Review this pull request. Plan the work with tasks_create first.",
},
maxSteps: 25,
});
// The completeness gate — one line, no model call:
const open = neurolink
.getTaskState("review-1421")
.items.filter((i) => i.status === "pending" || i.status === "in_progress");
if (open.length > 0) {
// hand the open items back to the agent: finish, delegate, or close with a reason
}
The tools
| Tool | Input | Behaviour |
|---|---|---|
tasks_create |
{ titles: string[] } |
Appends tasks. The engine assigns the ids (t1, t2, …); the model never picks one. Blank titles are dropped. |
tasks_update |
{ id, status, note? } |
pending → in_progress → done, or closed for work that will not be done. |
tasks_list |
{} |
Reads the checklist. Cheap, always current. |
All three return the whole checklist:
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 · 129 lines · 0 tokens per session scan A de62dad9165a
TASK-CHECKLIST is an agent published in the GitHub repository juspay/neurolink (128 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,224 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
claude-design-orchestrator
Parses claude.ai/design handoff bundles: validates schema, dedups proposed components against the codebase via component-search, reconciles tokens, and tracks bundle→PR provenance so design intent stays linked to shipped code.
vc-research-agent
RESEARCH MODE - Information gathering only. Use for understanding existing code, architecture, and context. Never suggests implementations or modifications.
vc-spec-agent
SPEC MODE - Product-discovery requirements doc for user review. Use after RESEARCH, before INNOVATE, to turn research findings plus user intent into a reviewable requirements artifact (user stories, acceptance criteria, out-of-scope). Never chooses an approach or writes implementation steps.
vc-execute-agent
EXECUTE MODE - Implementing EXACTLY what was planned. Full tool access. Can only be invoked after explicit user confirmation. Use after plan is approved.
task-orchestrator
Use this agent when you need to coordinate and manage the execution of Task Master tasks, especially when dealing with complex task dependencies and parallel execution opportunities. This agent should be invoked at the beginning of a work session to analyze the task queue, identify parallelizable work, and orchestrate…
command-system-agent
Specializes in Phase 5 command system implementation including natural language command parsing, /collective namespace commands, and intelligent autocomplete for enhanced user experience.