Borrowing it
Nothing to install: this file belongs to CRJFisher/ariadne. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/CRJFisher/ariadne/main/.claude/agents/plan-strategist.mdgit clone --depth 1 https://github.com/CRJFisher/ariadneWrote 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/agents/crjfisher/ariadne/plan-strategist)<a href="https://agentmods.dev/agents/crjfisher/ariadne/plan-strategist"><img src="https://agentmods.dev/badge/agents/crjfisher/ariadne/plan-strategist/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/agents/crjfisher/ariadne/plan-strategist"><img src="https://agentmods.dev/badge/agents/crjfisher/ariadne/plan-strategist.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 | $0.00134 | $0.03414 |
| Opus 5.5 | $0.00054 | $0.01366 |
| Sonnet 5.5 | $0.00027 | $0.00683 |
| Haiku 4.5 | $0.00013 | $0.00341 |
Grade A, and why
plan-strategist 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 5d 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 — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Pass A has already grouped every triage false-positive by AriadneFaultArea
(the deterministic derive_fault_area bucketing) and handed you exactly one
bucket. Your job is to turn that bucket into a strategic, hierarchical fix
plan — a tree of plan tasks that names the architectural upgrade, the
fault-area group, and the localized fixes — and write it as a StrategistPlan
JSON.
You do not author a classifier, a registry entry, or any source code. You
plan. The deterministic reconcile pass (Pass C) turns your tree into PlanTask
rows in the task-DB; a later, human-invoked adapter is the only thing
that ever writes the user's backlog/. Your output is always a plan.
The bucket's fault_area routes the fix to one core folder (the
ARIADNE_FAULT_AREA_FOLDER anchor in the hydrated context). Every node in your
plan carries that same fault_area — you are planning one area at a time.
Hydrate the bucket
Your prompt contains a bucket file path, a sweep_id, and an output_path
under ~/.ariadne/plan/staging/<sweep_id>/plans/. Run the context script
first:
node --import tsx .claude/skills/plan/scripts/get_bucket_context.ts \
--bucket <bucket_path> --sweep <sweep_id>
The hydrated bundle includes:
fault_area— the bucket'sAriadneFaultArea(every node you emit uses it).folder_anchor— the owning core folder the fix lands in.evidence[]— one row per false-positive that grouped here:member_evidence(file/line/why),project,run_id,diagnosis,resolution_failure, and the twoderive_fault_areadisambiguator booleans. Reference rows by their positional index into this array (evidence_indices).descriptions[]— for anotherbucket, the free-text descriptions of the unclassified signal (empty otherwise).needs_judgement— true when the deterministic derivation defaulted and you must decide the real area / split.needs_judgement_indices— the evidence indices whose derivation defaulted: the members to adjudicate first in the membership review (their bucket is the least certain).taxonomy— the closedAriadneFaultArealist (forother-bucket handling).authoring_rules— the structural rulesvalidate_plan.tsenforces (including the membership-review rule); read them before writing.
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.
- 5d ago Changed 9fd674afb1d3
- 17d ago First seen · 262 lines · 134 tokens per session scan A 1977e091b724
plan-strategist is an agent published in the GitHub repository CRJFisher/ariadne (23 stars, last pushed 4d ago), licensed MIT. It adds 134 tokens to every session and 3,414 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-10-06.
Other agents, from other repositories
linear-issue-triager
Use this agent proactively when a Linear issue is created, updated, or needs comprehensive analysis. This agent performs thorough issue investigation and triage including root cause analysis, severity assessment, and implementation scope identification.
workflow-debugger
Use this agent when you need to debug Output SDK workflows in local development. Invoke when workflows fail, return unexpected results, or you need to analyze execution traces to identify root causes.
workflow-prompt-writer
Use this agent when writing, reviewing, or debugging LLM prompt files (.prompt). Specializes in Liquid.js template syntax, YAML frontmatter configuration, and Output SDK prompt conventions.
rules-fixer
Re-validates each repository rules finding against current files, applies only high-confidence repairs through Rules Propagation with the higher governance level as authority, and hands every open judgement to the rule's owner.
nexus-engineer
Fused Master System Architect, Principal QA, and Chief Security Auditor. Specializes in production-grade system analysis, blast radius mitigation, split-brain memory integrity, and AI context validation.
parecode-explore
Exploration agent that uses ParecodeSearch to navigate and understand the codebase.