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/jonase47/ccpr/p3-arch-adrgit clone --depth 1 https://github.com/jonase47/ccprWrote 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/jonase47/ccpr/p3-arch-adr)<a href="https://agentmods.dev/commands/jonase47/ccpr/p3-arch-adr"><img src="https://agentmods.dev/badge/commands/jonase47/ccpr/p3-arch-adr.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 | $0.00000 | $0.01423 |
| Opus 5 | $0.00000 | $0.00711 |
| Sonnet 5 | $0.00000 | $0.00285 |
| Haiku 4.5 | $0.00000 | $0.00142 |
Grade A, and why
p3-arch-adr 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 today.
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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/p3-arch-adr – Write Architecture Decision Records
Documents all significant architectural decisions as ADRs.
Argument: $ARGUMENTS = [Specific decision, e.g. "ADR-0001 Monolith"]
If provided: Write ADR for the named decision. If not provided: Create ADRs for all open decisions from architecture and tech stack.
Prerequisites
- ARCHITECTURE.md and TECH_STACK.md exist
Agent
- Type: system-architekt
- Model: sonnet
Context (Orchestrator prepares)
Orchestrator reads beforehand and delivers inline:
- From ARCHITECTURE.md: Architectural decisions made (short list)
- From TECH_STACK.md: Technology decisions with alternatives
Prompt Template
Goal: Write ADRs for all significant architectural decisions.
Decisions: [inline from ARCHITECTURE.md + TECH_STACK.md]
Output Format: One file per ADR with:
- Title, date
- Context (1-2 sentences)
- Options (enumeration)
- Decision (1 sentence)
- Justification (1-2 sentences)
- Consequences (pros/cons as list)
Follow-ups and Addenda — once the ADR has shipped and open questions get answered later, apply the same two conventions this repository's own ADRs under
docs/adr/use (CONTRIBUTING.md, "Record an ADR's resolutions in place"):
- A resolved follow-up is struck through in place, with a pointer to what resolved it — never silently deleted:
~~**original wording**~~ **Resolved in Addendum N (DD.MM.YYYY): the answer, in one sentence.**- An addendum's heading names what it resolves:
## Addendum N (DD.MM.YYYY): <what it resolves>— a reader working down the follow-up list needs the heading to find the answer.Constraints:
- Only decisions with real alternatives (no trivial decisions)
- Numbering: ADR-0001, ADR-0002, etc. (four digits, matching this repository's own
docs/adr/convention)
Orchestrator Checkpoint
- Every ADR has context, options and justification?
- No redundant ADRs?
- Every ADR's frontmatter has
statusandadr_statusmapped correctly (never the decision word instatus)?
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.
- today Changed · +3 lines 9fc258c0974d
- 4d ago First seen · 124 lines · 0 tokens per session scan A c430d3689d9c
p3-arch-adr is a command published in the GitHub repository jonase47/ccpr (1 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,423 tokens. 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
wiki-tune
Tune wiki schema and conventions interactively.
listen
Show what a given agent should read before coding, plus briefs/approvals mentioning it.
pseo-init
Use when: kullanıcı "yeni proje", "init", "proje kur", "yeni domain ekle", "scaffold" gibi ifadeler kullanır ya da /pseo-init çağırırsa. Also use when: portföye yeni bir SEO projesi alındı, projects/{slug}/ klasörü ve project.config.json dosyasının schemaya uygun ilk hâli üretilecek; brief'te slug + domain + market…
forge-insights
Analyze past sessions for error patterns, file activity, and recommendations.
forge-context-status
Report on current context window usage, cache health, and compaction recommendation. Read-only — does not compact.
CLAUDE
Each subdirectory is one engine verb dispatched by ../cli/cli.ts: / .ts exports a pure handler that resolves the vault, does its work through ../core/ primitives, and returns its own typed report. Commands stay thin — they compose core checks and builders; they do not reimplement them. The canonical output schema is…