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/shiyas1331/devkit/whygit clone --depth 1 https://github.com/shiyas1331/devkitWhat 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 | $0.00059 | $0.00765 |
| Opus 5 | $0.00030 | $0.00382 |
| Sonnet 5 | $0.00012 | $0.00153 |
| Haiku 4.5 | $0.00006 | $0.00076 |
Grade A, and why
why 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.
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Why does this code exist? — router
This is a thin dispatcher. The picker fires when there's no flag; otherwise the command parses input and delegates to a sub-command. The full pipeline lives in commands/why/default.md — the canonical body that other sub-commands reference.
Response format — always:
- Start with the answer (one paragraph). The first sentence is the "why."
- Be direct. No marketing language.
Input
$ARGUMENTS
Routing rules — apply in order
1. Picker fires when no flag is present
Trigger:
$ARGUMENTSis empty, OR$ARGUMENTScontains only a target (file:line/file/file:start-end) with no--*flag
Use AskUserQuestion:
question: "How deep should I go?"
header: "Depth"
multiSelect: false
options:
- label: "Quick why (~10s answer)"
description: "One paragraph + sources + walk summary."
- label: "Thorough drilldown"
description: "Adds PR description, key review-thread debate, secondary edits."
- label: "JSON output"
description: "Machine-readable for tooling."
- label: "Custom (more flags)"
description: "Combine flags like --max-walk=10 or --depth + --json. Pick this then paste the full command."
If $ARGUMENTS has no target yet, prompt: "Target? (e.g. apiClient.ts:188, or apiClient.ts:120-150 for a range)".
Map answer → sub-command and re-invoke:
| Choice | Re-invoke |
|---|---|
| Quick why | /devkit:why <target> (default sub-command) |
| Thorough drilldown | /devkit:why <target> --depth=thorough |
| JSON output | /devkit:why <target> --json |
| Custom | (prompt user for the full command) |
2. Help token → delegate to help sub-command
Trigger: $ARGUMENTS contains --help, -h, or ? as a standalone token.
Delegate to commands/why/help.md.
3. Flag-based input → delegate to flag sub-command
| Pattern | Delegate to |
|---|---|
<target> --depth=thorough |
commands/why/thorough.md |
<target> --json |
commands/why/json.md |
<target> (bare, no flag) |
commands/why/default.md |
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 · 84 lines · 59 tokens per session scan A 09b5ca832200
why is a command published in the GitHub repository shiyas1331/devkit (4 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 765 once invoked, about $0.0003 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.