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 skills/rp1-run/rp1/tasknpx skills add rp1-run/rp1 --skill taskgit clone --depth 1 https://github.com/rp1-run/rp1Wrote 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/rp1-run/rp1/task)<a href="https://agentmods.dev/skills/rp1-run/rp1/task"><img src="https://agentmods.dev/badge/skills/rp1-run/rp1/task.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 | $0.00010 | $0.01782 |
| Opus 5 | $0.00005 | $0.00891 |
| Sonnet 5 | $0.00002 | $0.00356 |
| Haiku 4.5 | $0.00001 | $0.00178 |
Grade A, and why
task 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 4d 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 — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Queue Management
Interact with the rp1 persistent task queue. Tasks are stored in ~/.rp1/rp1.db and processed in FIFO order (oldest first). The task system is a queue and state tracker -- execution is the responsibility of the agent or harness hook that picks up the task.
Task Lifecycle
Tasks move through these states:
pending -> in_progress -> completed
-> failed
pending -> cancelled
in_progress -> cancelled
- New tasks start as
pending. pickupatomically transitions the oldest pending task toin_progress.- Only
in_progresstasks can be completed or failed. - Only
pendingandin_progresstasks can be cancelled.
Operations
Create a Task
Queue a new task for later execution.
rp1 agent-tools task create \
--type <type> \
--description <text> \
[--payload <json>] \
[--project <path>]
| Option | Required | Description |
|---|---|---|
--type |
Yes | Free-form task type (e.g., check-annotations, archive-feature, remediate-audit) |
--description |
Yes | Human-readable description of the work |
--payload |
No | JSON string with type-specific data |
--project |
No | Absolute project path for scoping (omit for global tasks) |
Example:
rp1 agent-tools task create \
--type "check-annotations" \
--description "Review open annotations from last audit" \
--project /Users/dev/myapp
Example with payload:
rp1 agent-tools task create \
--type "remediate-audit-findings" \
--description "Fix security issues found in auth module" \
--payload '{"files":["src/auth.ts","src/session.ts"],"severity":"high"}'
List Tasks
View tasks filtered by status and/or project.
rp1 agent-tools task list \
[--status <status>] \
[--project <path>] \
[--limit <n>]
| Option | Required | Description |
|---|---|---|
--status |
No | Filter by status: pending, in_progress, completed, failed, cancelled |
--project |
No | Filter by absolute project path |
--limit |
No | Maximum number of tasks to return |
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.
- 4d ago First seen · 280 lines · 10 tokens per session scan A c90f7250e190
task is a skill published in the GitHub repository rp1-run/rp1 (38 stars, last pushed 29d ago), licensed Apache-2.0. It adds 10 tokens to every session and 1,782 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 skills, from other repositories
apm-issue-autopilot
Use this skill to drive any open microsoft/apm issue (bug, feature, docs, refactor, perf) from raw intake to a mergeable PR with triage as the central, paramount gate. Run the apm-triage-panel rubric per issue first, then present ONE consolidated triage review for the whole batch and escalate to the maintainer BY…
apm-triage-panel
Use this skill to triage one microsoft/apm issue selected by the daily sweep, the status/needs-triage fast path, or manual dispatch. Emit one synthesized comment with a decision, label set, exact milestone, and suggested next action.
openspec-bulk-apply-change
Use when multiple active OpenSpec changes should be applied concurrently in isolated worktrees with delegated verification and no merge.
product-management
Expertise in product management lifecycle, from ideation to launch. Covers requirements gathering, user story creation, prioritization, and product strategy. Use this skill for product planning, writing PRDs, defining MVPs, or competitive analysis.
prd-to-plan
Turn a PRD into a multi-phase implementation plan using tracer-bullet vertical slices, saved as a local Markdown file in ./plans/. Use when user wants to break down a PRD, create an implementation plan, plan phases from a PRD, or mentions "tracer bullets".
openspec-new-change
Start a new OpenSpec change using the experimental artifact workflow. Use when the user wants to create a new feature, fix, or modification with a structured step-by-step approach.