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/dreamiurg/harness-map/deploygit clone --depth 1 https://github.com/dreamiurg/harness-mapWhat 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 | $0.00007 | $0.00016 |
| Opus 5 | $0.00003 | $0.00008 |
| Sonnet 5 | $0.00001 | $0.00003 |
| Haiku 4.5 | $0.00001 | $0.00002 |
Grade A, and why
deploy 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 2d 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.
What it actually says
Deploy the thing.
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.
- 2d ago First seen · 5 lines · 7 tokens per session scan A a2f7ac53e5d5
deploy is a command published in the GitHub repository dreamiurg/harness-map (2 stars, last pushed 8d ago), licensed MIT. It adds 7 tokens to every session and 16 once invoked, about $0.0000 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
scan
Resolve a target's dependencies into one consolidated graph, then optionally enrich, analyze, audit, and render it. scan is the pipeline every other graph command builds on — flags you learn here work the same way on explain and diff.
diff
Compare dependency state between two points — two Git refs, two SBOM files, or two container image tags — and report what changed. diff runs the scan pipeline against both states, so the same target flags and gates apply to each side.
explain
Answer "why is this package here?" — trace every dependency path that pulls a package into the graph. explain runs the same detect and match stages as scan, then walks the graph from the project roots to the package you named.
mmap
Open the live Mellos map in a terminal split pane beside this session.
plan_local
Create implementation plan with codebase analysis.
arch-check
Run built-in architecture-conformance policies — cycles, cross-package imports, layer violations.