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 instructions/raydestar/sir-thaddeus/notion-task-workflowgit clone --depth 1 https://github.com/raydeStar/sir-thaddeusWrote 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/instructions/raydestar/sir-thaddeus/notion-task-workflow)<a href="https://agentmods.dev/instructions/raydestar/sir-thaddeus/notion-task-workflow"><img src="https://agentmods.dev/badge/instructions/raydestar/sir-thaddeus/notion-task-workflow.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 | $0.02379 | $0.02379 |
| Opus 5 | $0.01189 | $0.01189 |
| Sonnet 5 | $0.00476 | $0.00476 |
| Haiku 4.5 | $0.00238 | $0.00238 |
Grade A, and why
Task Execution Workflow 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 5d 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 — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Execution Workflow
This workflow governs how every agent operates in the Sir Thaddeus repository. Follow these steps in sequence. Do not require Notion or any other external board to begin or complete work.
Core Rule
- The active user request is the source of truth unless the user explicitly points you at a GitHub issue, document, or tracker.
- External trackers are optional context, not a prerequisite.
- Never block implementation on updating a task board.
Progress Reporting Requirements
Progress commentary is mandatory throughout this workflow. The human operator must always know where you are, what you are doing, and whether you are stuck.
When to report progress
Report a progress update:
- After identifying the concrete task you are working on.
- After each significant implementation step.
- After every test run, with a plain-English summary of what passed, failed, or was skipped.
- Whenever you encounter a decision point that could change the outcome.
- Whenever you are about to slow down, retry, or change approach.
- Whenever something unexpected happens (a file is missing, a build fails, a tool errors).
What a progress update must include
Every update must state:
- What phase you are in.
- What you just completed.
- What you are doing next.
- Any open risk, uncertainty, or blocker you have noticed — even if you plan to push through it.
Escalation thresholds
| Situation | Action |
|---|---|
| Cannot start the task at all (dependency, external resource, missing access) | Report the task as Blocked immediately. Do not attempt partial work. |
| Made meaningful progress but hit a hard stop you cannot resolve | Leave the work in a reviewable state and report Needs Human Testing with the exact blocker. |
| Approximately 90% complete but the final step requires human interaction, live UI, or unverifiable execution | Report Needs Human Testing. Do not self-certify. Describe the remaining step precisely. |
| Fully complete and all tests pass | Proceed to the closeout phase. |
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.
- 5d ago First seen · 249 lines · 2,379 tokens per session scan A f2bcdc9db02e
Task Execution Workflow is an instructions file published in the GitHub repository raydeStar/sir-thaddeus (13 stars, last pushed 4d ago), licensed Apache-2.0. It adds 2,379 tokens to every session, about $0.0119 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 instructions, from other repositories
ironcurtain CLAUDE.md
Claude Code instructions for provos/ironcurtain, covering claude.md, general workflow, git & worktrees, git workflow and platform considerations.
run402 AGENTS.md
AGENTS.md instructions for kychee-com/run402, covering agents.md, what this is, git workflow — worktrees, never branches, never stash, build & test commands and run all unit tests.
TimeTree-MCP CLAUDE.md
Claude Code instructions for ehs208/TimeTree-MCP, covering timetree mcp project guide, project purpose, current capabilities, architecture map and api behavior notes.
llm-swarm-router AGENTS.md
AGENTS.md instructions for matthewdcage/llm-swarm-router, covering agent & developer guide, dox rail, project overview, architecture and repository layout.
llm-swarm-router CLAUDE.md
Claude Code instructions for matthewdcage/llm-swarm-router, covering claude code: swarm-llm and honcho memory (mcp).
mcp-local-llm AGENTS.md
Instructions for aplaceforallmystuff/mcp-local-llm, covering agents.md - mcp-local-llm, tech stack, architecture, development commands and environment variables.