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 skills/ahmadulhoq/agentskel/knowledge-routingnpx skills add ahmadulhoq/agentskel --skill knowledge-routinggit clone --depth 1 https://github.com/ahmadulhoq/agentskelWrote 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/skills/ahmadulhoq/agentskel/knowledge-routing)<a href="https://agentmods.dev/skills/ahmadulhoq/agentskel/knowledge-routing"><img src="https://agentmods.dev/badge/skills/ahmadulhoq/agentskel/knowledge-routing.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 | $0.00041 | $0.00835 |
| Opus 5 | $0.00020 | $0.00417 |
| Sonnet 5 | $0.00008 | $0.00167 |
| Haiku 4.5 | $0.00004 | $0.00084 |
Grade A, and why
knowledge-routing 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 4d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Routing
Purpose: Three layers exist — pick the right one.
The three layers
| Layer | Where it lives | Who owns it |
|---|---|---|
| Agent operational state | .memory/ in repo |
Agent, shared via git |
| Team-canonical knowledge | Confluence | Humans (tech leads, product) |
| Tracked work | Jira | Team |
Decision table
| Knowledge type | Destination | Why |
|---|---|---|
| Codebase structure (modules, classes, functions) | .memory/MAP.md, .memory/SYMBOLS.md |
Agent reads every session |
| Session state, what's next | .memory/RESUME.md |
Local-only, session handoff |
| Coding conventions (naming, style, patterns) | .memory/CONVENTIONS.md |
Read by every session |
| Agent lessons learned (mistakes to avoid) | .memory/LESSONS.md |
Small, agent-facing |
| Sacred behaviors (code that looks wrong but shouldn't change) | .memory/SACRED.md |
Small, agent-facing |
| Team roster and roles | .memory/TEAM.md |
Read during handoffs |
| Jira workflow conventions | .memory/JIRA_WORKFLOW.md |
Read before Jira writes |
| Tech debt findings | .memory/TECH_DEBT.md + optional Jira ticket |
Local record + tracked when actionable |
| Architectural decisions (ADRs) | Confluence (ADRs parent) + link in LESSONS.md | Team-canonical, durable |
| Post-mortems | Confluence (Postmortems parent) | Team-visible, searchable |
| Runbooks | Confluence (Runbooks parent) | Referenced during incidents |
| Feature specifications | Confluence (Specs parent) | Human-authored and -reviewed |
| Release notes | Confluence (or GitHub release) | External audience |
| Tracked work (features, bugs, debt being worked) | Jira | Lifecycle-tracked by team |
The rule
- Operational / per-agent →
.memory/ - Team-canonical / durable / referenced by humans → Confluence
- Lifecycle-tracked work → Jira
Cross-layer linking
When knowledge spans layers, cross-reference:
- ADR in Confluence → add one-line entry in
.memory/LESSONS.mdwith the Confluence link. So agents recall the decision without loading the full ADR. - Tech debt in TECH_DEBT.md → add
Ticket: PROJ-1234column when a Jira ticket tracks the work. - PR description → reference ticket key and link to Confluence spec if applicable.
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.
- 4d ago First seen · 64 lines · 41 tokens per session scan A 3a1242b59b24
knowledge-routing is a skill published in the GitHub repository ahmadulhoq/agentskel (13 stars, last pushed 20d ago), licensed MIT. It adds 41 tokens to every session and 835 once invoked, about $0.0002 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 2026-09-02.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…