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/matrixfounder/agentic-development/skill-archive-tasknpx skills add MatrixFounder/Agentic-development --skill skill-archive-taskgit clone --depth 1 https://github.com/MatrixFounder/Agentic-developmentWhat 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 | $0.00031 | $0.04431 |
| Opus 5 | $0.00015 | $0.02216 |
| Sonnet 5 | $0.00006 | $0.00886 |
| Haiku 4.5 | $0.00003 | $0.00443 |
Grade A, and why
skill-archive-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 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 — 365 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Archiving Protocol
This skill encapsulates the complete protocol for archiving docs/TASK.md to docs/tasks/
and docs/PLAN.md to docs/plans/ (in lockstep with TASK.md).
When to Archive
Archive docs/TASK.md ONLY when:
- Starting a NEW task AND
docs/TASK.mdexists with DIFFERENT content - Completing a task (Orchestrator Completion stage)
DO NOT archive when:
- Refining/clarifying the CURRENT task (overwrite instead)
docs/TASK.mddoes not exist
[!IMPORTANT] PLAN.md rotates in lockstep with TASK.md. Whenever TASK.md is archived for a NEW task, the old
docs/PLAN.md(if present) is archived too — see "PLAN.md Archiving (Lockstep)" below. On task refinement, PLAN.md is overwritten in place, never archived.docs/ARCHITECTURE.mdis a LIVING document and is never touched by this skill.
Decision Logic: New vs Refinement
IF user request implies a NEW SEPARATE feature/refactor:
→ Archive existing TASK.md, then create new
IF user request is a clarification/refinement of CURRENT task:
→ Overwrite TASK.md, do NOT archive
Indicators of NEW task:
- Different feature/component mentioned
- "Create new task for...", "Start working on..."
- Completed previous task
Indicators of REFINEMENT:
- "Clarify requirement X", "Add detail to..."
- Same feature context as current TASK.md
Protocol Steps
Step 1: Check Condition
IF NOT exists("docs/TASK.md"):
SKIP archiving → Create new TASK.md
Step 2: Extract Metadata
Read from current docs/TASK.md:
- Task ID from "0. Meta Information" section
- Slug from "0. Meta Information" section
If Meta Information is missing or malformed:
- Use slug from task title (H1 header)
- Generate ID via tool if available, otherwise use
000or increment last known ID manually.
Step 3: Generate Filename
The ID comes from the DOCUMENT, not from the directory. Step 2 already read it from the Meta block; Step 3 only confirms it is free and turns it into a filename.
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 · 365 lines · 31 tokens per session scan A 86e932df1d7a
skill-archive-task is a skill published in the GitHub repository MatrixFounder/Agentic-development (5 stars, last pushed 19d ago), licensed Apache-2.0. It adds 31 tokens to every session and 4,431 once invoked, about $0.0002 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
argent-tv-interact
Control and inspect TV apps via argent — Apple TV (tvOS), Android TV (leanback), and Amazon Fire TV (Vega). Boot the target, read focus, navigate with the D-pad remote, type, screenshot, and on Vega debug the JS runtime (evaluate, console logs, network inspector). Use when a task targets a TV (runtimeKind "tv", or…
review-offered-task
Review a task that has been offered to you and decide whether to accept or reject it.
company-hiring-intelligence
Reverse-engineer what a company is building by scraping their job postings, careers page, LinkedIn Jobs, and engineering blog using TinyFish web agents. Use whenever a user wants to understand a company's strategic direction from hiring signals, do competitive intelligence, figure out a tech stack from job…
文档协作
引导用户通过结构化的文档共同编写工作流程。当用户想撰写文档、提案、技术规范、决策文档或类似结构化内容时使用。该工作流程帮助用户高效传递上下文，通过迭代优化内容，并验证文档对读者有效。当用户提到写文档、创建提案、起草规范或类似文档任务时触发。.
aidd-dev:08:for-sure
Iterative agent loop that tracks attempts and retries until a success condition is met. Use when the user says "for sure", "make sure", "keep trying until", "loop until done", "don't stop until", or needs guaranteed completion of a task with explicit success criteria.
Swift Performance Optimization Skill
Use when investigating measured Swift or Apple-platform regressions in CPU, memory, launch, scrolling, animation hitches, image processing, energy, networking, or concurrency, or when designing performance tests and Instruments experiments. Do not use for speculative micro-optimization, ordinary refactoring, or a…