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 agents/foliveira/harmonia/knowledge-curatorgit clone --depth 1 https://github.com/foliveira/harmoniaWhat 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 | $0.00016 | $0.00174 |
| Opus 5 | $0.00008 | $0.00087 |
| Sonnet 5 | $0.00003 | $0.00035 |
| Haiku 4.5 | $0.00002 | $0.00017 |
Grade A, and why
knowledge-curator 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.
This is a copy
78% identical to committer — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Read these two files before acting; together they are your working contract:
- ${CLAUDE_PLUGIN_ROOT}/core/RULES.md
- ${CLAUDE_PLUGIN_ROOT}/core/charters/knowledge-curator.md
If either file cannot be read, stop and report the failing path - do not proceed uncharted.
When prior experience could help, retrieve relevant learnings with:
bash ${CLAUDE_PLUGIN_ROOT}/bin/memory/recall.sh
Work only inside your charter's authority, read your inputs from the task workspace paths you are given, and write your outputs to the workspace paths your charter names - the next agent consumes files, not conversation.
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 · 23 lines · 16 tokens per session scan A 42f8179677a4
knowledge-curator is an agent published in the GitHub repository foliveira/harmonia (2 stars, last pushed 17d ago), licensed MIT. It adds 16 tokens to every session and 174 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 78% identical to committer, differing in 6 lines, and is treated as a copy.
Other agents, from other repositories
code-explainer
Explains complex code in clear, understandable terms. Use when onboarding to a codebase, understanding unfamiliar patterns, or documenting legacy code.
developer-advocate
A developer advocate who bridges product and developer community — creating demos, writing tutorials, gathering feedback, and championing developer experience. Use for developer relations, SDK documentation, community engagement, and developer experience strategy.
git-specialist
A Git power user who designs branch strategies, resolves complex conflicts, cleans up history, and teaches teams to use Git as a precision tool — not a footgun. Use for rebasing, bisecting, history rewriting, merge strategies, and workflow design.
instructional-designer
An instructional designer who creates effective learning experiences — from onboarding programs to technical training, using learning science principles to ensure knowledge transfer and skill development. Use for training design, course development, learning assessment, and knowledge transfer strategy.
ijfw-extract-learnings
Use after a phase or milestone completes to mine artifacts for decisions, lessons, patterns, and surprises that should feed forward.
gsd-plan-checker
Verifies plans will achieve phase goal before execution. Goal-backward analysis of plan quality. Spawned by /gsd:plan-phase orchestrator.