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 commands/coleam00/context-engineering-intro/executegit clone --depth 1 https://github.com/coleam00/context-engineering-introWhat 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 | $0.00007 | $0.01141 |
| Opus 5 | $0.00003 | $0.00571 |
| Sonnet 5 | $0.00001 | $0.00228 |
| Haiku 4.5 | $0.00001 | $0.00114 |
Grade A, and why
execute scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
{Any curl commands or UI steps to manually verify the feature works.} This is a copy
100% identical to execute — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Execute: Implement an Archon Plan
Objective
Read and execute every task in the plan file: $ARGUMENTS
Implement all tasks faithfully, following Archon monorepo conventions, and report results.
Step 1: Read the Entire Plan
Read the plan file at $ARGUMENTS from start to finish before writing a single line of code.
Understand:
- All tasks and their dependencies
- Affected packages and files
- Architecture notes and prohibited patterns
- The validation steps at the end
Do NOT start implementing until you have the full picture.
Step 2: Verify Current State
Check the working tree is clean before starting:
git status
If there are uncommitted changes unrelated to this plan, flag them before proceeding.
Check the current branch:
git branch --show-current
Step 3: Execute Tasks in Dependency Order
Work through each task in the plan sequentially (respecting Depends on: ordering).
For each task:
- Read the target file(s) before modifying — never edit blindly.
- Implement the change using the Edit or Write tools.
- Verify the change compiles after touching TypeScript files:
Fix type errors immediately — do not accumulate them.bun run type-check 2>&1 | tail -20
Archon conventions to follow:
Imports:
// Type-only imports
import type { IPlatformAdapter, Conversation } from '@archon/core';
// Value imports — named, not namespace
import { handleMessage, pool } from '@archon/core';
// Submodule namespace imports (acceptable)
import * as git from '@archon/git';
Functions:
// All functions need explicit return types
async function createSession(id: string): Promise<Session> { ... }
// No implicit any
Logging:
import { createLogger } from '@archon/paths';
// Lazy logger pattern (test mocks work correctly)
let cachedLog: ReturnType<typeof createLogger> | undefined;
function getLog(): ReturnType<typeof createLogger> {
if (!cachedLog) cachedLog = createLogger('my-module');
return cachedLog;
}
// Event naming: {domain}.{action}_{state}
log.info({ id }, 'session.create_started');
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 · 190 lines · 7 tokens per session scan A 0ebb775661b6
execute is a command published in the GitHub repository coleam00/context-engineering-intro (13,813 stars, last pushed 5mo ago), licensed MIT. It adds 7 tokens to every session and 1,141 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 100% identical to execute, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.