constraint-first

A reasoning method that identifies the hardest technical, business, user, legal, or resource limits and designs around those limits first.

In plain words
What is it for?
Use it to rank project constraints, solve the most difficult one first, and check whether later decisions still work with it.
Why use it?
It tests the decisions most likely to block the project before spending time on easier details. Constraints that cannot be changed are made explicit instead of being silently ignored.

Agent

Part of the jhostalek-skills plugin — 32 skills, 12 agents shipped together

Install

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.

agentmods
npx agentmods add agents/jhostalek/dotclaude/constraint-first
Clone the repo
git clone --depth 1 https://github.com/JHostalek/dotclaude

Or install jhostalek-skills, the plugin that ships this one along with the rest of its 32 skills, 12 agents.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 131 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00131
Opus 5 $0.00000 $0.00066
Sonnet 5 $0.00000 $0.00026
Haiku 4.5 $0.00000 $0.00013

Measured 3d ago against content hash c8ff002e334e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

constraint-first 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.

skills/design/agents/constraint-first.md · 8 lines

What it actually says

Constraint-First Explorer

Your reasoning method: identify the hardest constraints and solve those first.

Rank every constraint (technical, business, user, regulatory, resource) by difficulty. Design for the single hardest one first, then add the next-hardest and check whether the solution survives — adapt it if not. Continue in difficulty order; easy constraints adapt around the hard decisions, handled last. If a constraint seems immovable, name it explicitly — don't silently assume it away.

Your blind spot: You may produce solutions that are defensively designed — technically sound but uninspiring. You may miss creative approaches that dissolve constraints rather than solving them.

Changes

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.

  1. 3d ago First seen · 8 lines · 0 tokens per session scan A c8ff002e334e

Subscribe to this mod's changes

constraint-first is an agent published in the GitHub repository JHostalek/dotclaude (11 stars, last pushed 28d ago), licensed CC0-1.0. It costs nothing until one of its globs matches a file; then it loads 131 tokens. 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.

Related

Other agents, from other repositories

experience-extractor

Learning agent for the Self-Evolving Loop. Use when executing /evolving-loop Phase LEARN — after completion-judge decides EVOLVE, when iterations fail with similar issues, before the evolve phase, or on SHIP to record success patterns. Runs evidence-based root-cause analysis, extracts patterns, writes learning.json…

claude-world/director-mode-lite · 127 tokens

skill-evolver

Evolution agent for the Self-Evolving Loop. Use when executing /evolving-loop Phase EVOLVE — after experience-extractor produces learning.json, when completion-judge decides EVOLVE, on an --evolve request, or on SHIP for lifecycle review. Applies verified learning to produce improved skill versions and manages…

claude-world/director-mode-lite · 120 tokens

agents-expert

Expert on creating and configuring custom Claude Code agents (subagents). Use PROACTIVELY when the user mentions creating an agent, custom agent, or subagent; when designing specialized agents for project tasks; when troubleshooting agent invocation, tools, or model config; or during /agents-generate. Knows the…

claude-world/director-mode-lite · 138 tokens

completion-judge

Decision-making agent for the Self-Evolving Loop. Use when executing /evolving-loop Phase DECIDE — after the validator writes validation.json, when an iteration cycle completes, or at a manual decision point. Applies the SHIP/FIX/EVOLVE/ABORT threshold rule against verified evidence and writes reports/decision.json.…

claude-world/director-mode-lite · 118 tokens

hooks-expert

Expert on Claude Code hooks — event-driven automation for tool calls, prompts, sessions, and notifications. Use PROACTIVELY when the user mentions "hook", "automation", or "trigger"; when designing PreToolUse/PostToolUse/Stop/UserPromptSubmit hooks or security guards; or during hook setup. Knows the hook event list…

claude-world/director-mode-lite · 129 tokens

skills-expert

Expert on creating, editing, and debugging Claude Code skills and slash commands. Use when the user mentions creating a skill or slash command, wants a reusable command-based workflow, when a skill fails to trigger, or during /skills-generate. Knows the official skill frontmatter fields, arguments, allowed-tools, and…

claude-world/director-mode-lite · 120 tokens