headcount is an organization of independently installable Claude Code plugins, each grouping skills for a department such as finance, security, or demand generation. Claude Code users install the departments they need and invoke their skills for specialized work; the catalogue entries are skills and related agent tooling from that organization.
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 cbrock84/headcount --skill estimating-and-contingencygit clone --depth 1 https://github.com/cbrock84/headcountWrote 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/cbrock84/headcount/estimating-and-contingency)<a href="https://agentmods.dev/skills/cbrock84/headcount/estimating-and-contingency"><img src="https://agentmods.dev/badge/skills/cbrock84/headcount/estimating-and-contingency.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00087 | $0.00968 |
| Opus 5 | $0.00044 | $0.00484 |
| Sonnet 5 | $0.00017 | $0.00194 |
| Haiku 4.5 | $0.00009 | $0.00097 |
Grade A, and why
estimating-and-contingency 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 3d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Estimating and contingency
An estimate is a claim about an uncertain future. Most organizations treat it as a commitment made by whoever said the number, which is why estimates are padded, disbelieved, and padded again.
Decompose before you estimate
Estimate the work, not the project. Break it down until each piece is small enough that someone who would do it can picture doing it — usually a week or two of effort. Below that you are estimating noise; above it you are guessing.
Two decomposition failures are worth naming. Missing scope is the larger one: integration, data migration, environments, testing, documentation, training, and the coordination overhead of everyone involved routinely go unestimated because nobody owns them. Double-counted contingency is the other: padding inside every task, then adding a reserve on top of the padded total.
Pick the method that matches what you know
- Analogous — scale from a comparable past effort. Fast, needs real history, and the comparison has to survive being stated out loud: what is genuinely similar and what is not.
- Parametric — a rate applied to a count. Cost per endpoint, per interface, per square foot, per test case. Credible only when the rate comes from your own data and the count is knowable.
- Bottom-up — estimate each decomposed piece and roll up. Most accurate, most expensive, and worth it once the work is understood well enough for the pieces to be real.
Use two methods and compare them where the number matters. When they disagree by more than a quarter, one of them is built on an assumption nobody has stated.
Write the basis down, because that is the durable part
The number is the least useful output. The basis of estimate is what lets someone re-estimate later instead of starting over: what is included, what is explicitly excluded, the rates and quantities used, the assumptions the number depends on, and who provided each input.
An estimate without a basis cannot be defended, cannot be updated, and cannot be learned from. When the project comes in at double, the basis is what tells you whether the estimate was wrong or the work changed — and those call for opposite responses.
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.
- 3d ago First seen · 80 lines · 87 tokens per session scan A 4dafe099046c
estimating-and-contingency is a skill published in the GitHub repository cbrock84/headcount (1,300 stars, last pushed 4d ago), licensed MIT. It adds 87 tokens to every session and 968 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 2026-09-03.
Other skills, from other repositories
user-story-map
Build an interactive, drag-and-drop user story map so the user can re-slice work across release phases. Use when the user wants a story map, a phased roadmap, release slicing, a backbone/activities journey map, or to decide "which stories go in which phase" and move them around.
agile-ledger
Plain-Markdown Scrum / Agile product-management system for Claude Code. Manage a product backlog of Epics and User Stories, plan and run sprints, drive a board, track velocity, cut Major.Minor releases, and keep GitHub branches/commits/PRs traceable to stories — all from slash commands, with no Jira and no database.…
agile-ledger-workspace
Optional multi-repo orchestrator for Agile-Ledger. Install once at a workspace root to manage many repositories at once: discover new repositories on a GitHub org (including ones nobody told you about), clone and bootstrap them, run a single cross-repo "what changed while I was away" sync, and reconstruct undocumented…
people-integration
Design the first 90 days for acquired product talent so they stay, contribute, and feel ownership. Produces decision map session template, mentor pairing matrix, 30/60/90 ownership plan, retention risk review (purpose and influence), and 1:1 coaching question library.
roadmap-convergence
Facilitate the post-acquisition roadmap convergence process across Weeks 1 to 8. Produces the conflict log, three-session facilitation guides, merged 90-day plus 12-month roadmap, and the 30/60/90 execution plan.
week-0-readiness
Run a product leader through pre-close (Week 0) integration readiness for an acquisition. Produces the integration lead charter, decision rights one-pager, combined product narrative draft, customer commitment inventory, and the five-question Day 1 readiness check.