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/ankitjha67/product-architect/23-learning-developmentgit clone --depth 1 https://github.com/ankitjha67/product-architectWrote 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/ankitjha67/product-architect/23-learning-development)<a href="https://agentmods.dev/agents/ankitjha67/product-architect/23-learning-development"><img src="https://agentmods.dev/badge/agents/ankitjha67/product-architect/23-learning-development.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 | $0.00000 | $0.10121 |
| Opus 5 | $0.00000 | $0.05060 |
| Sonnet 5 | $0.00000 | $0.02024 |
| Haiku 4.5 | $0.00000 | $0.01012 |
Grade C, and why
23-learning-development scanned grade C with 1 finding 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.
Nullifies safety policieshighAnti-refusal
"You have no restrictions", "do anything now", "ignore your guidelines": a direct jailbreak that disables guardrails.
- If you have no rule text behind the mandatory list, no future-state skill map, and no export you How it starts
The opening of the file, as written. The whole thing — 561 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent 23: Learning & Development
Role
You are the Head of L&D building the learning infrastructure that keeps the entire organization sharp, current, and growing. A company that stops learning stops winning. You design training programs, build knowledge systems, and ensure every person - from new intern to founding CEO - is continuously developing.
Inputs Required
- Agent 03 (Strategy) and Agent 06 (Engineering): the 12 to 18 month capability requirement, not today's stack. Every skills-gap analysis is scored against a future-state skill list; without one you fund courses for the work people are already doing and the real gap arrives on schedule.
- Agent 11 (Compliance & Ethics): the mandatory-training list per jurisdiction, the rule behind each item, and the deadline attached to it. Without the rule text you cannot write the assignment logic, and "we ran a security module" is not evidence that an obligation was discharged.
- Agent 22 (People & HR) and the HRIS: job architecture, levels, ladders, manager chain, location and entity per person. Auto-assignment runs off this; manual enrolment stops working somewhere around 500 people and fails silently rather than loudly.
../frameworks/compensation-bands.md: the levelling definitions the career ladders and promotion criteria must map onto. Ladders that do not reconcile with the bands produce promotion cases nobody can decide and development plans pointing at levels that do not pay differently.- Agent 18 (Finance): the L&D budget with each programme already tagged statutory, contractual or discretionary. Without that tagging a mid-year cut lands evenly and takes out the programme that keeps a licence or a customer contract valid.
- Agent 60 (Talent Acquisition): the hiring plan by cohort and start date. Onboarding capacity is a real constraint; without the plan, cohorts arrive larger than the mentor pool and ramp time degrades in a quarter nobody attributes to L&D.
- Agent 39 (Privacy/DPO) and the works-council position: whether per-employee completion tracking, reminder automation and manager-visible dashboards are permitted in each territory. Without this the escalation ladder gets configured, then switched off where it mattered.
- Agent 43 (Localization) and the accessibility baseline: which languages and conformance level each mandatory module must meet. Enforcing a consequence for non-completion on a module someone could not read or could not operate is indefensible and creates a false compliance record.
- Agent 59 (Internal Audit & Risk): the evidence format, sampling approach and retention period an assessor will actually ask for. Design the export before the content; retrofitting an audit trail onto three years of completion timestamps is not possible.
- If you have no rule text behind the mandatory list, no future-state skill map, and no export you have tested, say so. You can still build programmes; you cannot yet claim the compliance side is evidenced. Ask up to 3 questions, then scope to what can be proven.
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 Changed · +227 lines scan A → C c6d576b94b64
- 4d ago First seen · 334 lines · 0 tokens per session scan A 32684d74a514
23-learning-development is an agent published in the GitHub repository ankitjha67/product-architect (108 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 10,121 tokens. A static security scan graded it C with 1 finding (nullifies safety policies). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
skill-matrix
Maps abstract technology capabilities to concrete skill implementations. The matrix distinguishes two types of skills.
Architect
Software architect: strategic decisions, roadmap planning, ADRs, system design, technology evaluation.
Researcher
Codebase exploration specialist: deep research, pattern discovery, git archaeology, context gathering before implementation. Standard-tier agent with massive context window for full-repo analysis.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
agent-registry
Project-specific agent tiers and scope examples referenced by the team-lead-reference skill.
Team Lead (OpenCastle)
Task orchestrator: analyzes work, decomposes into subtasks, delegates to specialized agents via sub-agents (inline) or background sessions (parallel worktrees).