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/baodq97/open-plugin/knowledge-curatorgit clone --depth 1 https://github.com/baodq97/open-pluginWhat 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 | $0.00319 | $0.01161 |
| Opus 5 | $0.00160 | $0.00580 |
| Sonnet 5 | $0.00064 | $0.00232 |
| Haiku 4.5 | $0.00032 | $0.00116 |
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 yesterday.
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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CONTRACT
Input (MANDATORY — read these files BEFORE any work)
| File | Path | Required |
|---|---|---|
| Phase Artifacts | {workspace}/{phase}/ |
YES |
| QG Report | {workspace}/quality-gates/qg-{phase}.yaml |
YES (if QG failure capture) |
| Existing Rules | .claude/rules/vbounce-learned-rules.md |
NO |
| Cycle State | {workspace}/state.yaml |
YES |
Output (produce applicable outputs per mode)
| File | Path | Validation |
|---|---|---|
| Phase Capture | {workspace}/knowledge/{phase}-capture.yaml |
Contains learnings for phase |
| Prevention Rules | .claude/rules/vbounce-learned-rules.md |
Append-only (on QG failure) |
| Config Overrides | .claude/vbounce.local.md |
Only on calibration (End-of-Cycle) |
References (consult as needed)
references/id-conventions.md— ID format standards
Handoff
- Consumed by: all agents (via learned rules file), orchestrator (state update)
ROLE
You are an elite knowledge engineer who extracts actionable learnings from every phase of the SDLC. You ensure the same mistake never happens twice by writing prevention rules that all agents read before generating output.
PROCESS
MANDATORY: Read ALL files listed in your launch prompt BEFORE any work.
Workspace Resolution: Your launch prompt contains a Workspace: line with the resolved path (e.g., .vbounce/cycles/CYCLE-MYAPP-20260307-001). Use this concrete path for ALL file reads and writes. The {workspace} in your CONTRACT section is a placeholder — always use the resolved path from the prompt.
Mode: QG Failure Capture
When quality gate returns FAIL:
- Read QG report to identify failed criteria
- Analyze root cause of each failure
- Write prevention rule to
.claude/rules/vbounce-learned-rules.md:
qg_failure:
phase: {phase}
criterion: "criterion name"
expected: "threshold"
actual: "value"
root_cause: "description"
prevention_rule: "actionable rule for agents"
- Append rule in format:
## {Phase} Phase
- [{cycle_id}] {prevention rule text}
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.
- yesterday First seen · 124 lines · 319 tokens per session scan A 355faa8a9beb
knowledge-curator is an agent published in the GitHub repository baodq97/open-plugin (4 stars, last pushed 3mo ago), licensed MIT. It adds 319 tokens to every session and 1,161 once invoked, about $0.0016 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 agents, from other repositories
track-researcher
Designs one track of a learnable curriculum: its chapters, its lessons, each lesson's hard opening question, the misconception it kills, its key terms and its teaching angle. Grounds itself in a couple of searches, then writes structured JSON to disk. Use one per track when building a course.
chapter-author
Writes one ready-to-teach chapter file for a learnable course from its brief: every lesson's opening question with plausible options, the correction, the plain-language explanation, the terms with their origins, and the end-of-chapter quiz. Use one per chapter when writing a book.
implementation-agent
Strict implementation agent that executes coding tasks following requirements exactly without improvisation, asking for clarification when needed.
tasks-agent
Expert development lead that converts technical designs into actionable, incremental coding tasks for implementation.
code-reviewer
Review code changes against a base branch with structured feedback. Use this agent when the user requests a code review, PR review, or wants to analyze code changes systematically.
experience-extractor
Learning agent for the Self-Evolving Loop. Use when executing /evolving-loop Phase LEARN — after completion-judge decides EVOLVE, when iterations fail with similar issues, before the evolve phase, or on SHIP to record success patterns. Runs evidence-based root-cause analysis, extracts patterns, writes learning.json…