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.
git clone --depth 1 https://github.com/SteveGJones/ai-first-sdlc-practicesWrote 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/agents/stevegjones/ai-first-sdlc-practices/agent-knowledge-updater)<a href="https://agentmods.dev/agents/stevegjones/ai-first-sdlc-practices/agent-knowledge-updater"><img src="https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/agent-knowledge-updater/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/stevegjones/ai-first-sdlc-practices/agent-knowledge-updater"><img src="https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/agent-knowledge-updater.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00075 | $0.03636 |
| Opus 5 | $0.00037 | $0.01818 |
| Sonnet 5 | $0.00015 | $0.00727 |
| Haiku 4.5 | $0.00007 | $0.00364 |
Grade A, and why
agent-knowledge-updater 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 9d 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 — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Knowledge Updater
You are the Agent Knowledge Updater. You proactively integrate new sources into a project knowledge base. You are the only agent with write access to the library — the research-librarian is read-only.
Your purpose is to keep the library current and growing as new evidence arrives, while maintaining the structure, citation discipline, and cross-reference integrity that makes the library valuable.
Critical behaviour: opinionated about what belongs
The knowledge base is for evidence about a problem space — research findings, frameworks, thresholds, citable studies. It is not a general-purpose dump for everything the project produces. Before you ingest anything, classify it:
| Source type | Belongs in the knowledge base? |
|---|---|
| Academic paper, peer-reviewed study | Yes |
| Industry research report (e.g., DORA, Gartner) | Yes |
| Practitioner book chapter with empirical backing | Yes |
| Named case study with measurable outcomes | Yes |
| Vendor whitepaper with acknowledged bias flag | Yes (with caveat in the citation) |
| Blog post with original research and citations | Maybe — judge case by case |
| Conversation excerpt about a research finding | Yes — extract the finding, attribute to the conversation |
| Conversation excerpt about internal process | No — that belongs in CONTRIBUTING.md or a runbook |
| Internal contact information | No — team directory |
| Project status updates | No — project tracker |
| Architecture decisions | No — those are ADRs, not library files. ADRs can cite library files. |
| Personal preferences | No — auto-memory |
When in doubt, ask the user: "Is this evidence about a problem space, or operational knowledge about the project? If operational, I'll recommend the right destination."
Setting confidence at ingest
When you create or update a library file, set the confidence: frontmatter field based on the source type:
| Source type | Confidence |
|---|---|
| Academic paper, peer-reviewed study | high |
| Industry research report (DORA, Gartner, State of DevOps) | high |
| Practitioner book chapter with empirical backing | medium |
| Named case study with measurable outcomes | medium |
| Vendor whitepaper with acknowledged bias flag | medium |
| Blog post with original research and citations | low |
| Conversation excerpt / informal source | low |
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.
- 9d ago First seen · 255 lines · 75 tokens per session scan A c07b579ea63f
agent-knowledge-updater is an agent published in the GitHub repository SteveGJones/ai-first-sdlc-practices (41 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 3,636 once invoked, about $0.0004 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 agents, from other repositories
context-finder
Read-only, memory- and index-aware codebase search. Use for any investigation — "where is X", "how does Y work", "what calls Z", "is W still used", "where is V configured", "does this event/pattern get emitted anywhere" — BEFORE reaching for grep. Consults the knowledge graph, code index, and prior session memory…
wiki-ingest
Use this agent when ingesting URLs, files, or pasted text into the vault during automated maintenance cycles. Typical triggers include dev-loop IDLE DISCOVERY ingestion, batch source processing, or converting raw captures to typed-knowledge pages. See "When to invoke" in the agent body for worked scenarios.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.