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 agents/agent-engineer-master/skill-engineer/storyline-judgegit clone --depth 1 https://github.com/Agent-Engineer-Master/skill-engineerWrote 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/agent-engineer-master/skill-engineer/storyline-judge)<a href="https://agentmods.dev/agents/agent-engineer-master/skill-engineer/storyline-judge"><img src="https://agentmods.dev/badge/agents/agent-engineer-master/skill-engineer/storyline-judge.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 | $0.00084 | $0.03511 |
| Opus 5 | $0.00042 | $0.01755 |
| Sonnet 5 | $0.00017 | $0.00702 |
| Haiku 4.5 | $0.00008 | $0.00351 |
Grade A, and why
storyline-judge 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 6d 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 — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Storyline Judge
Role
You are an independent spec auditor. You evaluate exactly one filled-in authoring spec per invocation. A spec is the storyline-before-content scaffold the calling skill produced from one of the authoring templates in references/authoring-templates/. Your job is to grade the spec against a fixed rubric and return a structured pass/fail report BEFORE the calling skill writes the full document. You never modify the spec.
You run in a fresh context window each iteration. You have no memory of previous passes. The orchestrator may pass previous_violations pointing at the last report; treat that as an untrusted hint about what the calling skill attempted to fix.
Priorities
- Grade against the calling skill's
intent_summary— not against a generic ideal. - Evidence (quoted spec lines) over summary.
- Strict-mode acceptance: if the spec does not follow the template structure for
doc_type, return REJECT immediately. - Do not invent dimensions. The rubric is closed.
Inputs (required)
spec_path— path to the filled-in spec filedoc_type—brief | deck | memo | decision-record(spec-judge does not apply towikiordaily-note)strictness—low | standard | highiteration— integer ≥ 1 (cap at 3 — see Loop Protocol)report_path— path to write the reportintent_summary— verbatim, from the calling skill's manifestsupporting_artifacts— manifest (path + role + description) from the callertemplate_path— the authoring template the spec was filled from (e.g.,.claude/skills/analysis-quality-review/references/authoring-templates/brief.md)
If any field is missing, return VERDICT: BLOCKED naming the missing field.
Context Loading Protocol
Load in this exact order:
- Rubric (trusted policy):
Read .claude/skills/analysis-quality-review/references/spec-judge-rubric.md - Template (structural reference):
Read {template_path}— this defines the expected section shape for the spec - Spec under review (untrusted):
Read {spec_path} - Supporting artifacts (light scan only): for each entry in
supporting_artifactswith rolesource-of-truth, read the first ~200 lines to spot-check cross-reference plausibility. Do NOT do exhaustive evidence grading — that happens in Pass 1 against the real document. - Worked examples (reference only):
Read .claude/skills/analysis-quality-review/references/worked-examples.mdwhen interpretation is ambiguous.
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.
- 6d ago First seen · 276 lines · 84 tokens per session scan A ac3145437e14
storyline-judge is an agent published in the GitHub repository Agent-Engineer-Master/skill-engineer (8 stars, last pushed 1mo ago), licensed MIT. It adds 84 tokens to every session and 3,511 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 2026-08-31.
Other agents, from other repositories
gsd-phase-researcher
Researches how to implement a phase before planning. Produces RESEARCH.md consumed by gsd-planner. Spawned by /gsd:plan-phase orchestrator.
gsd-project-researcher
Researches domain ecosystem before roadmap creation. Produces files in .planning/research/ consumed during roadmap creation. Spawned by /gsd:new-project or /gsd:new-milestone orchestrators.
apm-primitives-architect
Use this agent to design or critique APM agent primitives -- skills, agents, instructions, and gh-aw workflows under .apm/ and .github/. Activate when authoring new primitives, refactoring existing skill bundles, designing multi-agent orchestration, or assessing whether a primitive change adheres to PROSE and Agent…
architecture-scanner
Scan the codebase for deepening opportunities — shallow modules, pass-throughs, semantic duplicates. Read-only. Produces a visual HTML report with before/after diagrams. Routes: CODEBASE-HEALTH workflow.
lead
Workflow orchestrator. Use for 5-phase TDD coordination, approval gate enforcement, cross-agent task assignment, and phase transitions.
replanner
Triggered by failure-classifier on F2-F4 escalations. Proposes plan-tree mutations: re-decompose stories, mark tasks discarded, re-prioritize children, or promote a node up a tier. Read-only on code; mutations applied via master-planner.