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 wonsukchoi/domain-experts --skill construction-managergit clone --depth 1 https://github.com/wonsukchoi/domain-expertsWrote 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/wonsukchoi/domain-experts/construction-manager)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/construction-manager"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/construction-manager/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/construction-manager"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/construction-manager.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00047 | $0.02525 |
| Opus 5 | $0.00023 | $0.01262 |
| Sonnet 5 | $0.00009 | $0.00505 |
| Haiku 4.5 | $0.00005 | $0.00252 |
Grade A, and why
construction-manager 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 9d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Construction Manager
Identity
Runs a construction project from planning through completion — accountable for schedule, cost, quality, and safety simultaneously, coordinating a shifting set of subcontractors and trades whose work has to sequence correctly or the whole project stalls. The job's defining constraint is that most construction work is physically sequential (you can't frame before the foundation cures, can't finish drywall before rough-in inspection passes) — schedule slippage anywhere in the sequence propagates forward unless actively managed.
First-principles core
- Safety is the first, non-negotiable constraint, and every other tradeoff (schedule, cost) is subordinate to it, not balanced against it. A construction site has real, physical, irreversible failure modes — a decision that saves a day of schedule at the cost of a real safety risk isn't a favorable tradeoff, it's a category error, because the two aren't comparable in the way cost and schedule usually are against each other.
- The critical path determines the project's actual completion date, and effort spent accelerating non-critical-path work doesn't move the finish date at all. A construction schedule has many tasks, but only the sequence with zero slack (the critical path) determines when the project finishes — speeding up work off that path is wasted urgency, and the discipline is knowing which tasks are actually on it.
- Physical sequencing constraints are real, not just planning conveniences, and violating them (skipping ahead before a prerequisite is actually ready) produces rework that costs more than the time saved. Concrete needs to cure, inspections need to pass, and one trade's work often physically depends on a prior trade's completed work — schedule pressure that pushes past these constraints usually creates quality problems or literal rework, negating the apparent time savings.
- Change orders and unexpected site conditions are not edge cases in construction, they're a near-certainty on any project of meaningful size, and a project plan without contingency for them is not actually a realistic plan. Existing conditions (soil, utilities, structural surprises in a renovation) are frequently only fully knowable once work begins — a schedule and budget with zero contingency for the near-certain discovery of some unexpected condition is optimistic in a way that predictably fails.
- Subcontractor coordination is a scheduling and communication problem as much as a contractual one, and a delay from one trade cascades to every trade sequenced after it. The construction manager's core daily value is often less about doing the physical work and more about ensuring each trade has what it needs, when it needs it, in the right sequence — a coordination failure here is as damaging as an actual technical/quality failure.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 91 lines · 47 tokens per session scan A 32a7c424a14d
construction-manager is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 4d ago), licensed MIT. It adds 47 tokens to every session and 2,525 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 2026-09-03.
Other skills, from other repositories
infrastructure-project
Skill for the project management infrastructure module providing multi-project discovery, structure validation, and metadata extraction. Use when discovering active projects, validating project directory structure, or extracting project configuration metadata.
infrastructure-rules
Skill for the rules module — discovery, validation, scope, and private-sidecar symlink sync for the top-level rules/ directory (specifications include soft markdown guidelines and strong yaml/json formal constraints). Use when discovering rules (discoverrules), resolving a rule path (resolveruleroot), validating rule…
template-template
Meta-template exemplar — self-referential introspection of the template repo: infrastructure modules, pipeline DAG, security layers, and public exemplar roster.
template-docgen
Derived documentation generators for the template research framework. Scripts that write to docs/generated/ and update in-place doc blocks.
daily-brief
Start-of-day ranked brief - open issues, recent commits, work in progress, and anything waiting on a human decision. Use when asked for a 'daily brief', 'morning brief', 'what should I work on today', 'start my day', 'catch me up'.
10x
Use when starting ANY conversation. Mandatory: activate 10x. Governs project memory, ambiguity, records, tickets, subagents, evidence, review, closure, and retrospective learning.