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/whchoi98/project-init/add-reference-docgit clone --depth 1 https://github.com/whchoi98/project-initWhat 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 | $0.00015 | $0.00925 |
| Opus 5 | $0.00008 | $0.00463 |
| Sonnet 5 | $0.00003 | $0.00185 |
| Haiku 4.5 | $0.00002 | $0.00093 |
Grade A, and why
add-reference-doc 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add Implementation Reference Doc
Append a skeleton implementation reference document for the given layer(s) under docs/reference/.
Step 1: Validate Layer Names
Target layers: $ARGUMENTS
Valid layers (enum):
infrastructuredataapiiacfrontenduisecurityagent-llm
If any argument is not in the enum, abort with: Unknown layer "<name>". Valid: infrastructure, data, api, iac, frontend, ui, security, agent-llm.
Step 2: Ensure Target Directory
mkdir -p docs/reference
Step 3: For Each Layer — Generate Skeleton
For every requested layer:
- Check existence at
docs/reference/{layer}.md:- If exists: prompt the user
overwrite / skip / abort. Onskipskip this layer; onabortabort the whole command.
- If exists: prompt the user
- Extract skeleton from
plugins/project-init/skills/project-scaffolder/references/reference-doc-template.md— read the fenced block under## Layer: {layer}. - Substitute variables:
{{COMPONENTS_TABLE}}→ empty table row| <!-- TODO: component --> | <!-- path --> | <!-- purpose --> |{{CODE_POINTERS_AUTO}}→<!-- TODO: add 3-7 code pointers -->
- Write to
docs/reference/{layer}.md.
Step 4: Regenerate docs/reference/INDEX.md
Read the current directory listing of docs/reference/*.md (excluding INDEX.md itself).
Rewrite the file with this structure:
# Implementation Reference Index / 구현 참조 인덱스
[](#english)
[](#korean)
<a id="english"></a>
## English
Layer-by-layer implementation guides. Each file follows the same 5-section
structure (Overview / Components / Key Decisions / Code Pointers / Cross-references).
<!-- AUTO-MANAGED:index -->
| Layer | File | Status |
|---|---|---|
| Infrastructure | [infrastructure.md](infrastructure.md) | present |
| Data | — | not applicable |
| API | — | not applicable |
| IaC | — | not applicable |
| Frontend | — | not applicable |
| UI | — | not applicable |
| Security | — | not applicable |
| Agent · LLM | — | not applicable |
<!-- /AUTO-MANAGED -->
Last updated: <today's date in YYYY-MM-DD> (managed by /init-project, /add-reference-doc, /sync-docs)
<a id="korean"></a>
## 한국어
(same structure, Korean section headings)
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 · 111 lines · 15 tokens per session scan A 569521944153
add-reference-doc is a command published in the GitHub repository whchoi98/project-init (2 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 925 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.
constitution
Create or update the project constitution from interactive or provided principle inputs.
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.