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 instructions/davidleconte/bob-llmwiki-knowledge-manager/agents-mdgit clone --depth 1 https://github.com/davidleconte/bob-llmwiki-knowledge-managerWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/davidleconte/bob-llmwiki-knowledge-manager/agents-md)<a href="https://agentmods.dev/instructions/davidleconte/bob-llmwiki-knowledge-manager/agents-md"><img src="https://agentmods.dev/badge/instructions/davidleconte/bob-llmwiki-knowledge-manager/agents-md.svg" alt="Measured on agentmods" height="20"></a>What 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 5.1 | $0.04628 | $0.04628 |
| Opus 5 | $0.02314 | $0.02314 |
| Sonnet 5 | $0.00926 | $0.00926 |
| Haiku 4.5 | $0.00463 | $0.00463 |
Grade A, and why
bob-llmwiki-knowledge-manager AGENTS.md 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 496 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to agents when working with code in this repository.
KB-First Protocol (read this before touching any source file)
This project maintains a pre-digested knowledge base at docs/knowledge-base/.
Before reading any raw source file, check the KB index first.
docs/knowledge-base/index.md ← master index of all digested knowledge
docs/knowledge-base/concepts/ ← architecture, caching, optimization, graph
docs/knowledge-base/guides/ ← setup, workflows, savings measurement
docs/knowledge-base/references/ ← API docs, estimation methodology
docs/knowledge-base/research/ ← audit findings, validation results, benchmarks
Mode-switch protocol: When you switch modes mid-session (knowledge-manager →
plan, plan → agent, etc.) your context resets. On the first task in the new mode,
check docs/knowledge-base/index.md for a KB doc covering the topic before
reading raw source. On N=10 curated well-formed pairs a KB hit replaced a full
source read for ≈51% fewer tokens; treat that as an illustrative upper band on
hand-picked pairs, not an all-pairs expectation (see §"Token Optimization System"
below for the exact assertion that backs it).
After every KB write (any mode): rebuild the knowledge graph so the new document is immediately queryable:
uv run bob-optimize graph-build --kb-path docs/knowledge-base --with-semantic
Quick KB map by task type:
| You need to… | Read this KB doc first |
|---|---|
| Understand the architecture | docs/knowledge-base/concepts/token-optimization.md + docs/architecture/architecture.md |
| Work on the cache | docs/knowledge-base/concepts/multi-level-caching.md |
| Audit cache thread-safety | docs/knowledge-base/concepts/cache-thread-safety-patterns.md |
| Work on the graph layer | docs/knowledge-base/concepts/knowledge-graph-layer.md |
| Work on delegation/pipeline | docs/knowledge-base/concepts/delegation-analysis-pipeline.md |
| Check test coverage / floors | docs/knowledge-base/research/coverage-measurement-2026-07-13.md |
| Understand savings claims | docs/knowledge-base/research/bobcoin-savings-analysis-2026-07-14.md |
| Understand KB document types | docs/knowledge-base/concepts/kb-document-types.md |
| Rename or move files | docs/knowledge-base/concepts/file-naming-conventions.md |
| Run a repo hygiene check | docs/knowledge-base/concepts/repo-hygiene-rules.md |
| Audit concurrency code | docs/knowledge-base/concepts/iterative-audit-methodology.md |
| Work on cost tracking | docs/knowledge-base/concepts/thread-safe-cost-tracking.md |
| Set up or install | docs/knowledge-base/guides/setup-token-optimization.md |
| Understand project status | STATUS.md (single authoritative source) |
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.
- 5d ago First seen · 496 lines · 4,628 tokens per session scan A 5c4b969f750a
bob-llmwiki-knowledge-manager AGENTS.md is an instructions file published in the GitHub repository davidleconte/bob-llmwiki-knowledge-manager (5 stars, last pushed 24d ago), licensed MIT. It adds 4,628 tokens to every session, about $0.0231 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 instructions, from other repositories
aeon CLAUDE.md
Claude Code instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
cognirepo CLAUDE.md
Claude Code instructions for ashlesh-t/cognirepo, covering claude.md, key rules, session start sequence (run in this order), behavioral confirmation rule and personas (cognirepo-402, cognirepo-403).
wayland-core copilot-instructions.md
Copilot instructions for FerroxLabs/wayland-core, covering ijfw rules, output discipline, memory routing, context discipline and cross-audit.
mcp-structured-memory CLAUDE.md
Claude Code instructions for nmeierpolys/mcp-structured-memory, a project described as: Structured Memory MCP Server.
inkwell-memory CLAUDE.md
Instructions for veronchenko/inkwell-memory, covering claude.md — inkwellmemory, layout, multi-tenant mode (inkwellmultitenant=1), conventions and testing.
memory-mcp-1file AGENTS.md
Instructions for pomazanbohdan/memory-mcp-1file, covering ⛔ l0 invariants (never violate under any circumstance), detection heuristic, 🔀 phase transition routing (⛔ blocking), gate-0: phase identification & loading and 🧾 proof-of-load requirement (critical).