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 agentmods add skills/melodic-software/claude-code-plugins/pick-for-the-problemnpx skills add melodic-software/claude-code-plugins --skill pick-for-the-problemgit clone --depth 1 https://github.com/melodic-software/claude-code-pluginsWrote 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/melodic-software/claude-code-plugins/pick-for-the-problem)<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/pick-for-the-problem"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/pick-for-the-problem.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 | $0.00138 | $0.01524 |
| Opus 5 | $0.00069 | $0.00762 |
| Sonnet 5 | $0.00028 | $0.00305 |
| Haiku 4.5 | $0.00014 | $0.00152 |
Grade A, and why
pick-for-the-problem 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 yesterday.
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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pick for the problem
A drift corrector for selection discipline: the tool must fit the problem,
not the reflex. The method, re-anchor, audit the work in flight, correct
forward, report, and the tone that firing this is not an accusation, lives
in
${CLAUDE_PLUGIN_ROOT}/context/re-anchor-audit-correct.md.
Read it; this file adds only what is specific to selecting a tool, library,
framework, language, or approach.
The discipline this re-anchors
A selection is a design decision, not a reflex. Resolve the source of truth
per the method doc's ladder: if the consuming project states a
technology-selection or dependency-adoption rule in its own CLAUDE.md /
.claude/rules/, re-anchor THAT. Otherwise re-anchor this portable
baseline.
The four selection sins, an unexamined choice usually traces to one:
- Habit. "I always use X." The reach is muscle memory, not analysis.
- Availability. "X is already at hand." Convenience picked it, not fit.
- Incumbency. "the repo already uses X, so new work assumes X." Current state is treated as the requirement.
- Preconception. "I came in believing X is the answer." The verdict preceded the problem.
The discipline that replaces them:
- Define the actual problem first. Name what is being solved, the real requirements, before any candidate is on the table. Do not let the first solution shape decide the problem.
- Survey the field. More than one candidate, judged against the stated requirements and the plausible future ones (variables that could shift and turn a choice into future pain).
- Walk the preference ladder, an earlier rung wins when it covers the
requirements and the plausible future requirements:
- Native. What the platform, language, or framework already provides: no new dependency, no new coupling.
- Official / authoritative, the first-party or canonical option when native falls short.
- Vetted third-party. Only when the rungs above genuinely miss, and only if it is well-maintained, well-known, safe, and secure.
- Every dependency is a coupling point. Weigh, at adoption time, the cost this coupling can impose later: abandonment, a pricing pivot, a license change, security posture, and exit cost. A dependency adopted without that weighing is an unpriced liability.
- Building what already exists is a finding. Re-implementing a solved, well-served problem (native or vetted) is a selection error in the other direction. Name it.
What ships with it
1 file 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.
- yesterday First seen · 125 lines · 138 tokens per session scan A 1b2890cef832
pick-for-the-problem is a skill published in the GitHub repository melodic-software/claude-code-plugins (15 stars, last pushed today), licensed MIT. It adds 138 tokens to every session and 1,524 once invoked, about $0.0007 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
parallel-orchestrator
Manage parallel Claude Code workstreams using git worktrees. Use when: splitting large tasks across multiple workers, coordinating parallel development, monitoring worker progress, integrating completed work, analyzing work item documents (code reviews, issue lists). Triggers: parallel, orchestrator, worktrees…
parallel-worker
Execute focused implementation tasks in a parallel workflow. Use when: working on assigned files in a worktree, making checkpoint commits, signaling dependencies or blockers, completing orchestrator-assigned tasks. Triggers: worker, checkpoint, worktree, assigned scope, commit prefix, parallel task.
build-priority-queue
For ordered processing: A search, Dijkstra, event simulation, task scheduling. Efficient min/max extraction with heap-based queue.
catch-expected-errors
For iteration with errors: catch exceptions during exploration, skip invalid cases, continue to next attempt.
compose-small-helpers
For complex behavior: build from tiny functions, chain transformations, make code read like a pipeline of operations.
count-combinations
For probability and counting: permutations, combinations, sample spaces, Monte Carlo simulation, brute-force enumeration, card/dice problems.