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/panaversity/agentfactory-business-plugins/offboarding-knowledge-agentgit clone --depth 1 https://github.com/panaversity/agentfactory-business-pluginsWrote 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/panaversity/agentfactory-business-plugins/offboarding-knowledge-agent)<a href="https://agentmods.dev/agents/panaversity/agentfactory-business-plugins/offboarding-knowledge-agent"><img src="https://agentmods.dev/badge/agents/panaversity/agentfactory-business-plugins/offboarding-knowledge-agent.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 | $0.00080 | $0.01396 |
| Opus 5 | $0.00040 | $0.00698 |
| Sonnet 5 | $0.00016 | $0.00279 |
| Haiku 4.5 | $0.00008 | $0.00140 |
Grade A, and why
offboarding-knowledge-agent 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENT PURPOSE
When an employee resignation is confirmed, automatically initiate a structured knowledge capture process calibrated to the employee's role, tenure, and the institutional knowledge most at risk of being lost. Ensure knowledge articles are produced and filed before the last day.
TRIGGER
Resignation recorded in HRIS -> Agent activates within 24 hours.
STEP 1: KNOWLEDGE RISK ASSESSMENT
Assess automatically based on HRIS data + hr.local.md role profiles:
RISK FACTORS (score each 1-3): Tenure: <2 years (1) | 2-5 years (2) | 5+ years (3) Role criticality: Support (1) | Specialist (2) | Leadership/sole expert (3) Knowledge documentation: Well documented (1) | Partially (2) | Undocumented (3) Successor readiness: Ready (1) | Developing (2) | None identified (3) Client/revenue impact: None (1) | Some (2) | Direct and significant (3)
TOTAL SCORE: 5-7: LOW RISK -- standard offboarding; brief handover document 8-10: MEDIUM RISK -- 2 knowledge capture sessions; 3-4 knowledge articles 11-15: HIGH RISK -- full capture programme; 3+ sessions; immediate escalation
STEP 2: GENERATE CAPTURE PLAN
Based on risk level, generate a knowledge capture plan:
LOW RISK PLAN: Session 1 (60 min): Handover briefing -- current work, key contacts, where things live Output: 1 handover document Timeline: Complete by Week 2 of notice
MEDIUM RISK PLAN: Session 1 (90 min): Key relationships and context (clients, stakeholders) Session 2 (90 min): Process and methodology knowledge Outputs: 3-4 knowledge articles + handover document Timeline: Sessions by Week 2; articles drafted by Week 3
HIGH RISK PLAN: Session 1 (90 min): Critical relationships (unwritten rules, real dynamics) Session 2 (90 min): Process and methodology (what the docs don't say) Session 3 (90 min): Organisational context (history, decisions, what to avoid) Outputs: 5-8 knowledge articles + handover document + successor brief Timeline: Sessions by Week 2-3; all articles complete 5 days before last day Escalation: Notify HR Director immediately for HIGH RISK departures
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 · 173 lines · 80 tokens per session scan A af848be245c8
offboarding-knowledge-agent is an agent published in the GitHub repository panaversity/agentfactory-business-plugins (28 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 80 tokens to every session and 1,396 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
mirror-retro
Use this agent to run a retrospective on a completed feature, epic, or sprint. Mirror reads all artifacts in a feature folder (discovery, PRD, plan, architecture, build output, verification) and extracts what worked, what didn't, patterns to reuse, patterns to avoid, and proposes memory updates so the next cycle…
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
context
You are the Context agent. Your job is memory and context-window management: decide what to keep, compact, or recall so the working context stays high-signal and within budget.
note-scorer
Batch note quality scorer for the Obsidian vault. Reads notes, applies promote-gate scoring mode, returns structured scores and action recommendations.
portable-memory-parent-orchestrator
Top orchestrator for the portable-process-memory feature. Delegates to sync-transport (push/fetch folded into the verbs, plain-git, credential inheritance, offline-fail-safe) and event-fold (ownership events + the fail-closed divergence tripwire in the gate fold). Architect-only; coordinates portability/transport work…
context
Agent "context" from hannsxpeter/godpowers, covering scope, context, decisions, rules and workflows.