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/validmind/atryum/atryumgit clone --depth 1 https://github.com/validmind/atryumWhat 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 | $0.00009 | $0.00337 |
| Opus 5 | $0.00005 | $0.00169 |
| Sonnet 5 | $0.00002 | $0.00067 |
| Haiku 4.5 | $0.00001 | $0.00034 |
Grade A, and why
atryum 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
Set up Atryum approval gating for this OpenCode project.
Reference files:
- @examples/opencode-plugin/atryum.ts
- @examples/opencode-plugin/README.md
Workflow:
- Briefly explain what the plugin does.
- If the user has not already told you their Atryum base URL, ask for it and default to
http://localhost:8080. - If the user has not already given you a bearer token or token-minting command, explain how to get one from their Atryum web login and ask them to paste it. Wait for the user's reply before making file changes.
- Once you have what you need:
- copy
@examples/opencode-plugin/atryum.tsto.opencode/plugins/atryum.ts - write the secret config to
~/.config/opencode/atryum.jsonso it stays out of git - set the secret config file mode to
0600 - store
urlplus eitheraccessTokenortokenCommand - never echo the secret back in chat after it is provided
- copy
- If the user explicitly asks for project-local storage instead, write
.opencode/atryum.jsoninstead of the global config file and still keep it mode0600. - When you finish, list the files you created or changed and remind the user to restart OpenCode so the plugin loads.
If the user prefers short-lived OAuth, offer to store a tokenCommand instead of a raw accessToken.
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 · 25 lines · 9 tokens per session scan A 5034c113d693
atryum is a command published in the GitHub repository validmind/atryum (11 stars, last pushed 21d ago), licensed Apache-2.0. It adds 9 tokens to every session and 337 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 2026-08-30.
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.