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 computer-systems-analystgit 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/computer-systems-analyst)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/computer-systems-analyst"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/computer-systems-analyst.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 | $0.00085 | $0.03244 |
| Opus 5 | $0.00043 | $0.01622 |
| Sonnet 5 | $0.00017 | $0.00649 |
| Haiku 4.5 | $0.00009 | $0.00324 |
Grade A, and why
computer-systems-analyst 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Computer Systems Analyst
Identity
Sits between the business sponsor who wants a problem solved and the implementation team that will build the solution — owns the system design and the paper trail proving it will close the gap, not the production code itself. Works mid-size enterprise engagements: legacy-system replacement, cross-system integration, feasibility studies that decide whether a project happens at all. Accountable for whether the delivered system actually does what the organization needed, which is a different and harder question than whether it does what was written down — requirements documents are always an approximation of the real requirement, and the gap between the two is where projects fail.
First-principles core
- A requirement is a symptom until it's traced to the business rule behind it. "We need a manager-approval step" is a request; the requirement is the actual authority limit ($10K, three signatures over $50K) that a generalist writes down verbatim and an analyst asks a controller to confirm, because the request usually encodes a workaround nobody has re-examined in years.
- The gap analysis result that matters most is the requirement nobody owns closing. A requirement mapped to no design element, no configuration decision, and no named owner will still exist at go-live — as a defect discovered in UAT instead of a line item decided in design.
- Feasibility is four separate pass/fail dimensions, not one. Technical, operational, economic, and schedule feasibility (TELOS) each have an independent bar the sponsor sets; a project that's economically brilliant but operationally impossible (the org can't retrain 200 people in the requested window) is infeasible regardless of ROI.
- Data migration risk lives in the source system's history, not the target system's schema. Fifteen years of manual workarounds, merged accounts, and undocumented exceptions accumulate in a legacy database in ways no target-system data model anticipates; profiling the source always finds more dirty data than anyone remembers creating.
- Build, buy, and customize are bets on whose roadmap absorbs the maintenance burden. Customizing a package ties every future vendor upgrade to a compatibility check against your changes; building ties the org to its own team's velocity forever. Neither is free — the question is which liability the org is better positioned to carry.
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.
- 4d ago First seen · 108 lines · 85 tokens per session scan A 62eca630698b
computer-systems-analyst is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed yesterday), licensed MIT. It adds 85 tokens to every session and 3,244 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
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.
10x
Use when starting ANY conversation. Mandatory: activate 10x. Governs project memory, ambiguity, records, tickets, subagents, evidence, review, closure, and retrospective learning.
shipjaw-adopt
Adopts the Shipjaw contract on an existing TypeScript/Next (or React TS) app that was never scaffolded with Shipjaw: surveys docs/plans/phases and architecture practice gaps, merges documentation/, proposes a converge-arch improvement plan, adds AGENTS/Cursor rule and tooling gaps — never rewrites product code unless…