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/done-0/openarche/knowledge-savegit clone --depth 1 https://github.com/Done-0/openarcheWhat 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 | $0.00010 | $0.00367 |
| Opus 5 | $0.00005 | $0.00183 |
| Sonnet 5 | $0.00002 | $0.00073 |
| Haiku 4.5 | $0.00001 | $0.00037 |
Grade A, and why
knowledge-save 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
Use this command to save one explicit piece of reusable engineering knowledge into the local OpenArche store.
For repository-specific work, prefer the repository-local store at .openarche/knowledge/.
Use the global store only when the user is saving cross-project knowledge on purpose.
What to save:
- durable decisions
- reusable patterns
- non-obvious gotchas
- high-signal fixes
Do not save:
- one-off chatter
- unresolved ideas
- project-specific notes with no reuse value
- obvious facts that do not improve future execution quality
When writing a knowledge item, require these fields:
titletype:solution,decision,pattern, orgotchastructure:atomic,linear,tree, orgraphtrigger_contexttagsbody
When saving:
- Find the correct OpenArche data directory.
- Read and validate the current config.
- Load the current
index.json. - Build the embedding from the same recall text the product uses:
title + " " + trigger_context. - Create a new knowledge id unless the user is explicitly updating an existing item.
- Write the markdown file under
<store>/knowledge/<id>.md. - Write the matching index entry.
If the user is updating an existing knowledge item:
- keep the existing id stable
- keep the file name and index id aligned
- do not silently create a duplicate entry
When reporting back:
- say whether a new item was created or an existing item was updated
- show the id
- summarize the saved title, type, and trigger context
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 · 54 lines · 10 tokens per session scan A 529a4d9d8d2c
knowledge-save is a command published in the GitHub repository Done-0/openarche (12 stars, last pushed 4mo ago), licensed MIT. It adds 10 tokens to every session and 367 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 2026-08-30.
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.