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/ainsteinsbr/renata/landscapegit clone --depth 1 https://github.com/AInsteinsBR/renataWrote 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/ainsteinsbr/renata/landscape)<a href="https://agentmods.dev/commands/ainsteinsbr/renata/landscape"><img src="https://agentmods.dev/badge/commands/ainsteinsbr/renata/landscape.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 | $0.00038 | $0.01319 |
| Opus 5 | $0.00019 | $0.00660 |
| Sonnet 5 | $0.00008 | $0.00264 |
| Haiku 4.5 | $0.00004 | $0.00132 |
Grade A, and why
landscape 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 4d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/renata:landscape — Competitive research to find your differentiation gaps
You map the solutions that already exist for the problem in the PRD, and help find where this product differentiates — without copying competitors or bloating the solution. You generate/update docs/research/<date>-landscape.md.
This is optional and runs after the PRD (the hypotheses must be clear). It works in two phases and detects which one it's in.
Respond to the user and generate document content in the user's language (the language they are writing in).
Phase detection
- If there is NO
docs/research/*-landscape.md, or it exists with raw research only (status🔬, no curation table filled) → Phase 1. - If a research dump exists awaiting curation → Phase 2.
Phase 1 — Research + dump (asynchronous)
- Read
@docs/prd/(problem, persona, hypotheses). The research is anchored on this. - Resolve the research source (MCP fallback): read
integrations:in.claude/rules.yaml. If theresearchcapability has an MCP configured AND its tools are available in the session (e.g. Perplexity) → use it. Otherwise → use nativeWebSearch/WebFetch. Tell the user which source you're using. - Research: direct competitors, indirect alternatives, and "how they solve it today without a product". Top 3-5 relevant ones — not a market census.
- For each solution: what it does well, what's missing, who it's for, pricing — always with a source (URL). No source → don't record as fact (set aside as "unverified" if relevant).
- Build the capability matrix (you × competitors) and list candidate gaps.
- Mark (as a suggestion) the gaps that look most promising for differentiation, with the why. Clearly a suggestion, not a verdict.
- Save everything to
docs/research/<date>-landscape.md(status🔬) and STOP: tell the user "I researched X solutions, found Y candidate gaps — it's all in . Read it at your own pace; when ready, run/renata:landscapeagain and we'll curate it together."
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.
- 4d ago First seen · 93 lines · 38 tokens per session scan A af3d890994e0
landscape is a command published in the GitHub repository AInsteinsBR/renata (10 stars, last pushed 13d ago), licensed MIT. It adds 38 tokens to every session and 1,319 once invoked, about $0.0002 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
issue-review
Run Codex native + adversarial review against the active issue, scoped to allowedfiles, capped per kind.
issue-closeout
Triage Codex findings via per-finding dispositions, mark findingstriaged, close the active issue.
prd-review
Review the active PRD with Codex and stream normalized findings to JSONL.
prd-triage
Triage pending findings on the active PRD.
prd-archive
Archive the active PRD (terminal state).
issue-start
Load a DSSE issue spec and begin structured work.