First Principles Review
Purpose
Use this as a lightweight decision review before another Aegis workflow makes a
directional choice. It is a compositional skill, not a standalone workflow.
Do not replace brainstorming, systematic-debugging, writing-plans,
requesting-code-review, or verification-before-completion. Use it to clean
the decision surface those skills will act on.
When this review materially changes the direction, surface Aegis Visibility
in natural prose: name the first principle, dropped assumption, smallest
sufficient path, or owner / retirement falsifier that changed the decision.
Keep it advisory and task-specific; do not turn the lens into approval
authority or a generic skill trace.
Use When
- The user asks for first principles, first-principles thinking, or Occam's
razor.
- A design, plan, or fix has multiple plausible paths and unclear selection
criteria.
- The task has ambiguous goals, competing constraints, or product/architecture
direction risk.
- Debugging is drifting into repeated fixes, fallback growth, duplicate owners,
consumer-side patches, or "just add another branch" reasoning.
- A review finds that the implementation may be locally correct but directionally
wrong.
Do Not Use
- Simple Q&A, status checks, tiny wording/config edits, or clearly bounded
single-owner changes.
- Mechanical execution of an approved plan unless a new directional conflict
appears.
- As a required step for every task, every turn, or every TDD cycle.
Five-Line Review
Answer only what is needed, usually in five short lines:
First Principle: What irreducible outcome must this satisfy?
Non-negotiables: What constraints cannot be broken?
Assumptions to Drop: What is habit, inherited shape, or unproven preference?
Smallest Sufficient Path: What is the least complex path that satisfies the first principle?
Escalation Signal: What finding would require spec/design/architecture review?
For repair choices, "smallest" means smallest sufficient stable repair, not the
smallest textual diff:
Minimality Check:
- Smallest textual diff:
- Correct owner:
- Bug class fixed:
- New branch/fallback added:
- Old path retired or scheduled:
- Verdict: sufficient repair | local patch | needs first-principles review
Decision Hygiene Review
Use this escalation only when a design, fix, or plan needs endorsement before it
is written into a spec or implementation plan.
Escalate from the five-line review when any of these risk signals appear:
- multiple plausible paths and no clear selection criteria
- a new owner, duplicate owner, fallback, adapter, or compat-only carrier
- an old path that may need delete-first handling or a retirement trigger
- an unverified assumption that the proposal depends on
- user language such as "more elegant", "long-term stable", "first
principles", or "Occam"
- a plan could encode the wrong owner, abstraction, compatibility boundary, or
retirement schedule
Use this compact shape:
First-principles invariants:
- Non-negotiable goal:
- Non-negotiable constraints:
- Historical assumptions to delete:
Owner / retirement matrix:
- New canonical owner:
- Old owner:
- Compat-only carrier:
- Delete-first / retirement trigger:
Falsification matrix:
- Dependency-removal test:
- Counterexample scenario:
- Must fail / degrade / remain correct cases:
Verdict:
- Adopt / revise / reject / needs evidence:
- Blocking gaps:
- Next evidence:
Architecture Integrity Lens
Use this narrower lens when a proposal is executable but may still encode the
wrong owner, abstraction, contract boundary, or retirement path. It is advisory
method-pack output and may be embedded inside Decision Hygiene Review when
that is enough.
Trigger it when any of these appear before approach selection, task
decomposition, review, or completion-risk reporting:
- responsibilities may overlap or a canonical owner is unclear
- the smallest diff adds a caller-side fallback, guard, adapter, or compat-only
carrier
- an existing source-of-truth or contract could solve the class of problem at a
higher level
- a stale owner, fallback, or old path may keep carrying real logic
- the work makes a long-term stability, "cleaner architecture", or
higher-level simplification claim
Use this compact shape:
Architecture Integrity Lens:
- Invariant: What must remain true for the system to be coherent?
- Canonical owner / contract: Which owner, contract, or source-of-truth should carry the behavior?
- Responsibility overlap: What duplicate owner, caller-side patch, fallback, or stale path might still carry real logic?
- Higher-level simplification: Can the problem be solved at the owner / contract / source-of-truth layer instead of by another local branch?
- Retirement / falsifier: What old path retires, or what evidence would disprove this architecture judgment?
- Verdict: proceed | revise design | split owner | return to baseline | needs ADR/baseline sync
Do not run this lens for every low-risk task. If it does not change the
decision surface, return to the active workflow immediately.
Composition
- With
brainstorming: run before approach selection when the request is broad,
ambiguous, likely to inherit a poor product shape, or involves owner /
retirement / fallback / adapter risk. Use Decision Hygiene Review or the
narrower Architecture Integrity Lens before recommending or selecting an
approach when those signals appear.
- With
systematic-debugging: run after evidence shows repeated fixes, fallback
growth, duplicate owners, or consumer-side patching.
- With
writing-plans: run before task decomposition when the plan could encode
the wrong owner, abstraction, compatibility boundary, fallback, adapter, or
retirement schedule. If the approved spec did not already cover this, use
Decision Hygiene Review or the Architecture Integrity Lens before writing
tasks.
- With
requesting-code-review: run when review should check direction and
owner integrity, not just code quality.
- With
verification-before-completion: use only to name residual directional
risk. It does not grant completion authority.
Boundaries
- Prefer evidence from current project files, baseline docs, tests, logs, and
user requirements. If evidence is missing, mark the line as unknown rather
than inventing a principle.
- Keep the result advisory. This skill may recommend escalation, but it does
not create authoritative
GateDecision, PolicySnapshot, or completion
authority.
- If the five-line review does not change the decision surface, return to the
active workflow immediately.
Source: hashgraph-online/awesome-codex-plugins → plugins/GanyuanRan/Aegis/skills/first-principles-review/SKILL.md
1---2name: first-principles-review3description: "Use when explicitly asked for first-principles or Occam's-razor review, or when complex decisions involve competing constraints, repeated fixes, fallback growth, duplicate owners, or architecture/product direction risk."4category: engineering-core5source_repo: hashgraph-online/awesome-codex-plugins6source_path: "plugins/GanyuanRan/Aegis/skills/first-principles-review/SKILL.md"7source_url: https://github.com/hashgraph-online/awesome-codex-plugins/blob/HEAD/plugins/GanyuanRan/Aegis/skills/first-principles-review/SKILL.md8metadata:9 source: https://skillmd.com/skills/hashgraph-online/first-principles-review10---111213# First Principles Review1415## Purpose1617Use this as a lightweight decision review before another Aegis workflow makes a18directional choice. It is a compositional skill, not a standalone workflow.1920Do not replace `brainstorming`, `systematic-debugging`, `writing-plans`,21`requesting-code-review`, or `verification-before-completion`. Use it to clean22the decision surface those skills will act on.2324When this review materially changes the direction, surface `Aegis Visibility`25in natural prose: name the first principle, dropped assumption, smallest26sufficient path, or owner / retirement falsifier that changed the decision.27Keep it advisory and task-specific; do not turn the lens into approval28authority or a generic skill trace.2930## Use When3132- The user asks for first principles, first-principles thinking, or Occam's33 razor.34- A design, plan, or fix has multiple plausible paths and unclear selection35 criteria.36- The task has ambiguous goals, competing constraints, or product/architecture37 direction risk.38- Debugging is drifting into repeated fixes, fallback growth, duplicate owners,39 consumer-side patches, or "just add another branch" reasoning.40- A review finds that the implementation may be locally correct but directionally41 wrong.4243## Do Not Use4445- Simple Q&A, status checks, tiny wording/config edits, or clearly bounded46 single-owner changes.47- Mechanical execution of an approved plan unless a new directional conflict48 appears.49- As a required step for every task, every turn, or every TDD cycle.5051## Five-Line Review5253Answer only what is needed, usually in five short lines:5455```text56First Principle: What irreducible outcome must this satisfy?57Non-negotiables: What constraints cannot be broken?58Assumptions to Drop: What is habit, inherited shape, or unproven preference?59Smallest Sufficient Path: What is the least complex path that satisfies the first principle?60Escalation Signal: What finding would require spec/design/architecture review?61```6263For repair choices, "smallest" means smallest sufficient stable repair, not the64smallest textual diff:6566```text67Minimality Check:68- Smallest textual diff:69- Correct owner:70- Bug class fixed:71- New branch/fallback added:72- Old path retired or scheduled:73- Verdict: sufficient repair | local patch | needs first-principles review74```7576## Decision Hygiene Review7778Use this escalation only when a design, fix, or plan needs endorsement before it79is written into a spec or implementation plan.8081Escalate from the five-line review when any of these risk signals appear:8283- multiple plausible paths and no clear selection criteria84- a new owner, duplicate owner, fallback, adapter, or compat-only carrier85- an old path that may need delete-first handling or a retirement trigger86- an unverified assumption that the proposal depends on87- user language such as "more elegant", "long-term stable", "first88 principles", or "Occam"89- a plan could encode the wrong owner, abstraction, compatibility boundary, or90 retirement schedule9192Use this compact shape:9394```text95First-principles invariants:96- Non-negotiable goal:97- Non-negotiable constraints:98- Historical assumptions to delete:99100Owner / retirement matrix:101- New canonical owner:102- Old owner:103- Compat-only carrier:104- Delete-first / retirement trigger:105106Falsification matrix:107- Dependency-removal test:108- Counterexample scenario:109- Must fail / degrade / remain correct cases:110111Verdict:112- Adopt / revise / reject / needs evidence:113- Blocking gaps:114- Next evidence:115```116117## Architecture Integrity Lens118119Use this narrower lens when a proposal is executable but may still encode the120wrong owner, abstraction, contract boundary, or retirement path. It is advisory121method-pack output and may be embedded inside `Decision Hygiene Review` when122that is enough.123124Trigger it when any of these appear before approach selection, task125decomposition, review, or completion-risk reporting:126127- responsibilities may overlap or a canonical owner is unclear128- the smallest diff adds a caller-side fallback, guard, adapter, or compat-only129 carrier130- an existing source-of-truth or contract could solve the class of problem at a131 higher level132- a stale owner, fallback, or old path may keep carrying real logic133- the work makes a long-term stability, "cleaner architecture", or134 higher-level simplification claim135136Use this compact shape:137138```text139Architecture Integrity Lens:140- Invariant: What must remain true for the system to be coherent?141- Canonical owner / contract: Which owner, contract, or source-of-truth should carry the behavior?142- Responsibility overlap: What duplicate owner, caller-side patch, fallback, or stale path might still carry real logic?143- Higher-level simplification: Can the problem be solved at the owner / contract / source-of-truth layer instead of by another local branch?144- Retirement / falsifier: What old path retires, or what evidence would disprove this architecture judgment?145- Verdict: proceed | revise design | split owner | return to baseline | needs ADR/baseline sync146```147148Do not run this lens for every low-risk task. If it does not change the149decision surface, return to the active workflow immediately.150151## Composition152153- With `brainstorming`: run before approach selection when the request is broad,154 ambiguous, likely to inherit a poor product shape, or involves owner /155 retirement / fallback / adapter risk. Use `Decision Hygiene Review` or the156 narrower `Architecture Integrity Lens` before recommending or selecting an157 approach when those signals appear.158- With `systematic-debugging`: run after evidence shows repeated fixes, fallback159 growth, duplicate owners, or consumer-side patching.160- With `writing-plans`: run before task decomposition when the plan could encode161 the wrong owner, abstraction, compatibility boundary, fallback, adapter, or162 retirement schedule. If the approved spec did not already cover this, use163 `Decision Hygiene Review` or the `Architecture Integrity Lens` before writing164 tasks.165- With `requesting-code-review`: run when review should check direction and166 owner integrity, not just code quality.167- With `verification-before-completion`: use only to name residual directional168 risk. It does not grant completion authority.169170## Boundaries171172- Prefer evidence from current project files, baseline docs, tests, logs, and173 user requirements. If evidence is missing, mark the line as unknown rather174 than inventing a principle.175- Keep the result advisory. This skill may recommend escalation, but it does176 not create authoritative `GateDecision`, `PolicySnapshot`, or completion177 authority.178- If the five-line review does not change the decision surface, return to the179 active workflow immediately.180181---182183**Source:** [`hashgraph-online/awesome-codex-plugins`](https://github.com/hashgraph-online/awesome-codex-plugins) → `plugins/GanyuanRan/Aegis/skills/first-principles-review/SKILL.md`