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 skills add erphq/skills --skill resource-managementgit clone --depth 1 https://github.com/erphq/skillsWrote 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/erphq/skills/resource-management)<a href="https://agentmods.dev/skills/erphq/skills/resource-management"><img src="https://agentmods.dev/badge/skills/erphq/skills/resource-management.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 | $0.00059 | $0.02132 |
| Opus 5 | $0.00030 | $0.01066 |
| Sonnet 5 | $0.00012 | $0.00426 |
| Haiku 4.5 | $0.00006 | $0.00213 |
Grade A, and why
resource-management 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 7d 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Resource Management — Under 100 People
What This Process Does
Resource management at this size is the discipline of matching the right person to the right project at the right time without burning out the team or leaving billable capacity on the table. You have 5–50 people allocatable across 5–30 active projects; founder or PM-lead manages allocations; tooling is spreadsheet-first or simple (Float, Resource Guru, Runn, PM-tool-native like Asana Workload).
The work: forecast demand, match supply, balance utilization, plan ahead 4–8 weeks, and adjust as projects shift. Mistakes: over-allocation (people on 3 projects at 50% each + meetings + admin = 200%); under-allocation (billable people not billable enough); no forward visibility (next-month surprises).
Start Here: ERP•AI Templates
ERP•AI's Small Business Resource Planning template provides skill + capacity registry, project-staffing requests, allocation visibility, utilization tracking, and 4–8 week forward visibility. Pair with Time & Expense for actuals + budget tracking.
Build — Setting It Up
With Agents
- Skill + capacity registry: Per-person — skills, certifications, available hours per week, time-off plans.
- Project-staffing requests: New project → required skills + hours + duration; PM submits; resource manager allocates.
- Real-time allocation view: Per person, current + future allocations across projects.
- Conflict detection: Person allocated >100% in week → alert.
- Utilization reporting: Billable hours / available hours per person + aggregate. Trending.
- Hire-vs-staff decisions: Forward demand vs. supply; data for hiring + contractor decisions.
- Time-off + holiday integration: PTO + holidays factored into capacity.
- Project-end transitions: Tech rolls off project; agent surfaces availability for next-project staffing.
Key Decisions
- Tool choice:
- Spreadsheet (Google Sheets, Excel): Lowest cost; works for ≤20 people
- Float: Visual scheduling; intuitive; popular for agencies
- Resource Guru: Similar to Float; team-utilization views
- Runn: Forward-looking forecasting + capacity planning
- Asana Workload / Monday Workload / ClickUp Workload: PM-tool-native; integrated
- Forecast (forecast.it): More sophisticated forecasting
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.
- 7d ago First seen · 162 lines · 59 tokens per session scan A ffc76a3e5391
resource-management is a skill published in the GitHub repository erphq/skills (2 stars, last pushed 18d ago), licensed MIT. It adds 59 tokens to every session and 2,132 once invoked, about $0.0003 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 skills, from other repositories
increment
Plan a unit of work as a SpecWeave increment - spec.md with Problem, Scope, numbered ACs and an Approach, plus tasks.md. Use when starting a feature, bug, hotfix or refactor.
sw-do
Implement a SpecWeave increment task by task through the ledger, with evidence per task and a verified close. Use for "implement this", "start working", "continue the increment", "keep going".
sw-task
Claim, finish, skip and release SpecWeave tasks via the append-only ledger so many agents share one increment. Use for "claim a task", "mark task done", "what next", "who owns T-03".
do
Work an increment task by task through the ledger: task next, claim, implement, commit, task done with evidence. Use when saying "implement", "start working", or "continue increment".
sw-increment
Open a SpecWeave increment - a numbered folder with spec.md (problem, scope, numbered ACs, approach) and tasks.md - before any code. Use for "plan a feature", "new increment", "let's build X".
done
Close an increment: ledger check, specweave verify, optional review, then specweave complete. Use when all tasks are done and saying "close increment", "we are done", or "finish up".