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.
git clone --depth 1 https://github.com/boparaiamrit/skills-by-amritWrote 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/commands/boparaiamrit/skills-by-amrit/execute)<a href="https://agentmods.dev/commands/boparaiamrit/skills-by-amrit/execute"><img src="https://agentmods.dev/badge/commands/boparaiamrit/skills-by-amrit/execute/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/boparaiamrit/skills-by-amrit/execute"><img src="https://agentmods.dev/badge/commands/boparaiamrit/skills-by-amrit/execute.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00020 | $0.01050 |
| Opus 5 | $0.00010 | $0.00525 |
| Sonnet 5 | $0.00004 | $0.00210 |
| Haiku 4.5 | $0.00002 | $0.00105 |
Grade A, and why
execute 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 9d 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/execute — Plan Execution
Execute an implementation plan task by task. Uses the
executing-plansskill with deviation protocol, checkpoint system, andplanning-tools.cjsfor state management.
Usage
/execute — Execute the current plan (from STATE.md position)
/execute [plan-name] — Execute a specific plan
/execute --continue — Continue from last checkpoint
Prerequisites
Before execution:
- A plan exists in
.planning/plans/with proper task anatomy (<files>,<action>,<verify>,<done>) .planning/STATE.mdexists (run/init-projectfirst)- The project builds and tests pass (pre-flight check)
Instructions
Step 1: Load Plan and State
# Load current state
node planning-tools.cjs state load
# Verify structure
node planning-tools.cjs verify structure
Read the plan file. If $ARGUMENTS specifies a plan, load that. Otherwise, find the current plan from STATE.md position.
Step 2: Pre-Flight Checks
// turbo
git status
Verify:
- Working tree is clean (no uncommitted changes)
- Build passes
- Existing tests pass
If pre-flight fails, STOP. Fix before executing.
Step 3: Announce and Confirm
"Plan: [name]
Tasks: [N] tasks, estimated [M] minutes
Context budget: [2-3 tasks, should complete in ~50% context]
Starting Task 1. Ready?"
In auto mode (config.mode = "auto"), skip confirmation.
Step 4: Execute Tasks
Use the executing-plans skill. For each task:
- Read task fully:
<files>,<action>,<verify>,<done> - Check context — if > 70%, checkpoint before starting
- Implement per
<action>(including DON'T/AVOID rules) - Verify by running every
<verify>command - Confirm every
<done>criterion - Commit atomically
- Advance state:
node planning-tools.cjs state advance-task
Step 5: Handle Deviations
If the plan doesn't match reality:
| Category | Action |
|---|---|
| Cosmetic | Fix silently, note in commit |
| Minor | Document in commit, proceed |
| Moderate | STOP → Report → Get approval → Proceed |
| Major | STOP → Return to planning |
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.
- 9d ago First seen · 173 lines · 20 tokens per session scan A 69017379df3f
execute is a command published in the GitHub repository boparaiamrit/skills-by-amrit (5 stars, last pushed 5mo ago), licensed MIT. It adds 20 tokens to every session and 1,050 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 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.