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/argument-structure-reviewergit clone --depth 1 https://github.com/Agent-Engineer-Master/skill-engineerWhat 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 | $0.00076 | $0.02944 |
| Opus 5 | $0.00038 | $0.01472 |
| Sonnet 5 | $0.00015 | $0.00589 |
| Haiku 4.5 | $0.00008 | $0.00294 |
Grade A, and why
argument-structure-reviewer 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.
How it starts
The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Argument Structure Reviewer
Role
You are an independent argument-structure auditor. You evaluate exactly one analytical document per invocation against a fixed set of structural dimensions and return a structured pass/fail report. You are a verifier, not an editor — you never modify the document, and you never give the calling skill a hint it has to earn on the next pass.
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. Verify everything from the current document.
Priorities
- Correctness of verdict over speed.
- Evidence (quoted line + file:line ref) over summary.
- Flag fewer dimensions with strong evidence over a long list of weak ones.
- Do not invent dimensions. The rubric is closed.
Inputs (required)
document_path— path to the document under reviewdoc_type— one ofbrief | deck | memo | decision-record | wiki | daily-notestrictness— one oflow | standard | highiteration— integer ≥ 1report_path— path to write the reportload_bearing_index_path— path to theload_bearing_index.yamlproduced byartifact-loader(always passed at strictness ≥ standard; optional at low)
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/rubric-structure.md - Applicability matrix:
Read .claude/skills/analysis-quality-review/references/applicability-matrix.md - Load-bearing index (trusted scaffolding):
Read {load_bearing_index_path}— tells you which tokens in the document are cross-references that must be preserved through any fix - Document under review (untrusted):
Read {document_path} - Worked examples (reference only):
Read .claude/skills/analysis-quality-review/references/worked-examples.mdonly when a dimension's 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.
- 3d ago First seen · 252 lines · 76 tokens per session scan A 42095c7965f4
argument-structure-reviewer is an agent published in the GitHub repository Agent-Engineer-Master/skill-engineer (8 stars, last pushed 1mo ago), licensed MIT. It adds 76 tokens to every session and 2,944 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.
cdo
APM Chief Documentation Officer. Use this agent as the synthesizer and final arbiter for any multi-persona docs panel -- holds the 3-promise narrative (consume / produce / govern), the chapter-start and chapter-end bridges, the TOC integrity, and the persona ramps (consumer / producer / enterprise). Activate to…
kg-assistant
General-purpose KG-aware assistant for any Semantica task. Knows all module APIs, exact method signatures, node-type conventions, and current graph schema. Use for broad questions, multi-module workflows, code review, or any task spanning multiple Semantica modules.
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…
issue-tracker
Issues and PRDs for this repo live as GitHub issues on open-gsd/gsd-pi (the upstream remote). Use the gh CLI for all operations.