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/nitineeen/beerman/task-executornpx skills add nitineeen/beerman --skill task-executorgit clone --depth 1 https://github.com/nitineeen/beermanWhat 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 | $0.00021 | $0.00450 |
| Opus 5 | $0.00010 | $0.00225 |
| Sonnet 5 | $0.00004 | $0.00090 |
| Haiku 4.5 | $0.00002 | $0.00045 |
Grade A, and why
task-executor 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 yesterday.
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.
What it actually says
Task Executor Flow
Follow this workflow for every task:
- Context Initialization:
- Check if a project is already open in the active session.
- If not, call
list_projects(). Perform a fuzzy search on the returned projects against the target name / repository name (e.g. mapping "Beerman" to "beer-man", "project beerman", "BeerMan", "beerman-monorepo", etc.). - If a matching project is found: Ask the user "I found the project '[Project Name]'. Would you like to connect to this project? Let's start." and wait/proceed on confirmation.
- If no matching project is found: Ask the user "No memory found for '[Project Name]'. Would you like to create a new project?" before running
create_project.
- Context Search:
- Query project memory using
search_memorywith keywords relevant to the active task. - If no results are returned (e.g. brand new project), proceed normally and note this in the final write-back.
- Query project memory using
- Execution:
- Perform the code changes or analysis.
- Verification:
- Build or run tests (e.g.,
npm run build) or review the file diff to verify correctness.
- Build or run tests (e.g.,
- Memory Update:
- Call
store_memorywith a summary of the change, affected files, and decisions. If this is the project's first task, note that in the summary. - If an image or screenshot memory was processed (OCR and relation-finding), ensure that the resulting findings, extracted content, and matching codebase files/relations are documented and stored back in memory using
store_memory(using the appropriate category, e.g.designorarchitecture). - Log code changes made, created files, completed phase plan steps, and project milestones to Supermemory via
store_memory(using the appropriate category, e.g.,roadmapordecision) so that the project history remains continuously synchronized.
- Call
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.
- yesterday First seen · 26 lines · 21 tokens per session scan A bf8e9cf16538
task-executor is a skill published in the GitHub repository nitineeen/beerman (0 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 450 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…