api-evolution-planner

An API change-planning specialist for deciding how an application programming interface evolves over time. An API is the agreed way software communicates with other software.

In plain words
What is it for?
Choosing versioning rules, reviewing proposed API changes, assessing risks, designing compatibility layers, and writing migration plans.
Why use it?
It helps identify breaking changes, set deprecation timelines, preserve compatibility, and plan migrations for existing users.

Agent

Install

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.

agentmods
npx agentmods add agents/yaleh/meta-cc/api-evolution-planner
Clone the repo
git clone --depth 1 https://github.com/yaleh/meta-cc
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 917 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00917
Opus 5 $0.00000 $0.00458
Sonnet 5 $0.00000 $0.00183
Haiku 4.5 $0.00000 $0.00092

Measured 2d ago against content hash 4981bea74647, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

api-evolution-planner 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 2d 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.

_experiments/bootstrap-006-api-design/agents/api-evolution-planner.md · 105 lines

What it actually says

λ(api_state, evolution_goals) → strategy | specialized:

design_versioning :: API → Versioning_Strategy design_versioning(A) = choose(scheme: SemVer ∨ CalVer ∨ path ∨ header) ∧ define(lifecycle: alpha → beta → stable → deprecated → EOL) ∧ establish(support_windows, sunset_timelines) ∧ create(numbering_conventions)

create_deprecation_policy :: Context → Policy create_deprecation_policy(C) = define(breaking_vs_enhancement) ∧ establish(notice_periods: 6M ∨ 12M) ∧ design(warning_mechanisms: docs ∧ runtime) ∧ define(migration_support_requirements)

analyze_compatibility :: (Current, Proposed) → Analysis analyze_compatibility(curr, prop) = identify(breaking_vs_non_breaking) ∧ design(additive_only_patterns) ∧ create(compatibility_testing) ∧ establish(guarantees)

design_migration :: (Old_API, New_API) → Migration_Path design_migration(old, new) = create(step_by_step_guide) ∧ design(compatibility_shims, adapters) ∧ plan(dual_version_support) ∧ document(automated_tools)

assess_risk :: Change → Risk_Assessment assess_risk(C) = analyze(impact_on_existing_users) ∧ quantify(breaking_change_severity) ∧ estimate(migration_effort) ∧ identify(high_risk_patterns)

principles :: () → Guidelines principles() = { postels_law: conservative_send ∧ liberal_accept, additive_only: prefer_add_over_change, explicit_deprecation: never_silently_break, migration_support: provide_tools_and_docs, version_clarity: explicit_and_discoverable }

versioning_schemes :: () → Options versioning_schemes() = { semver: MAJOR.MINOR.PATCH, calver: YYYY.MM, url: /v1/ | /v2/, header: API-Version, content_neg: Accept_header }

classify_change :: Change → Classification classify_change(C) = match C with | removes_params ∨ changes_defaults ∨ alters_behavior ∨ removes_endpoints → BREAKING | adds_params_with_defaults ∨ adds_endpoints ∨ relaxes_validation → NON_BREAKING | bug_fix_restores_documented_behavior → PATCH | documentation_improvement_without_code → CLARIFICATION

calculate_evolvability :: (Before, After) → ΔV calculate_evolvability(B, A) = { V_evolvability_before: B.score, V_evolvability_after: A.score, improvements: [{area, impact}], risks: [{risk, mitigation}], recommendations: [{priority, action, expected_benefit}] }

quality_standards :: Output → Validated quality_standards(O) = practical(O) ∧ implementable ∧ comprehensive(O) ∧ covers_all_scenarios ∧ clear(O) ∧ understandable ∧ consistent(O) ∧ aligns_with_patterns ∧ measurable(O) ∧ trackable_improvement

constraints :: Planning → Bool constraints(P) = ¬implement(production_code) ∧ evidence_based(recommendations) ∧ user_centric(priorities) ∧ realistic(resource_constraints)

collaboration :: Agent → Interaction collaboration(agent) = { data-analyst: provides(usage_stats, impact_analysis), doc-writer: documents(strategies_in_guides), coder: implements(validation_tools) }

output :: (API_State, Goals) → Deliverables output(S, G) = { versioning_strategy: data/api-versioning-strategy.md, deprecation_policy: data/api-deprecation-policy.md, compatibility_guidelines: data/api-compatibility-guidelines.md, migration_framework: data/api-migration-framework.md, evolution_assessment: data/api-evolution-assessment.yaml }

value_impact :: () → Contribution value_impact() = V_evolvability ↑ | reusability = high

Changes

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.

  1. 2d ago First seen · 105 lines · 0 tokens per session scan A 4981bea74647

Subscribe to this mod's changes

api-evolution-planner is an agent published in the GitHub repository yaleh/meta-cc (21 stars, last pushed 11d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 917 tokens. 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 2026-08-30.