AFPS Cost vs Progress Analysis

Scope: local Claude Code and Codex histories, rich session logs, git history, and repository task evidence from the first explicit AFPS adoption marker through the current request.

Analysis window: 2026-05-22 20:58:20 ET to 2026-05-29 17:58:06 ET. Comparison window: the same 6.875-day span immediately before that marker.

Verdict

Financial ROI is still negative, as expected, because no revenue is visible in the local evidence. The operating return is much better: since adopting AFPS, the work shifted into explicit route correction, alignment gates, product-path handling, skill-pack reliability, and showcase proof. That is progress toward a reusable operating system, not immediate cash return.

The nuance: raw commit count fell compared with the prior benchmark-remediation sprint, but post-AFPS work touched far more unique paths and carried stronger deliberation signals. The pre-window had 276 commits and 47 user prompts, mostly benchmark and fixture churn. The AFPS window had 121 commits, 588 user prompts, 2,065 unique paths touched, 26 explicit AFPS references, 81 analysis/review prompts, and 55 shipping/validation prompts.

Subscription utilization is high, but not evenly maxed. Claude carried most user-visible work: 415 of 588 post-AFPS prompts. Codex carried 173 prompts and 2,106 token-count events, with Pro plan logs showing no cap pressure above 7% primary window and 18% weekly window. In plain terms: the subscriptions are being used heavily, but ChatGPT Pro still had meaningful headroom during this window.

588post-AFPS user prompts across Claude and Codex
235post-AFPS sessions
121post-AFPS git commits in this repo
$69-$92estimated subscription spend for this window
458.6Mlogged token events, including cached context
26explicit AFPS markers in prompt history

Verdict Gate

Does this headline conclusion match your lived sense of the AFPS period?

Source Coverage

CategoryCoverageUse in report
Claude compact history~/.claude/history.jsonl, 9,799 linesUser prompt counts, sessions, projects, AFPS marker examples, command usage.
Codex compact history~/.codex/history.jsonl, 1,899 linesUser prompt counts, sessions, AFPS marker examples, command usage.
Codex rich sessions~/.codex/sessions/**/*.jsonl, 661 filesSession metadata, cwd enrichment, model/provider, token-count events, plan type, rate-limit utilization.
Claude rich project sessions~/.claude/projects/**/*.jsonl, 481 filesDeduped request-level token usage by requestId, model mix, service tier, cwd context.
Repository git historygit log, git numstat, git diff-treeCommits, additions/deletions, files touched, file categories, added alignment/test/benchmark artifacts.
Repo task/docs evidencetasks/todo.md, tasks/roadmap.md, tasks/history.md, docs/skill-next-step-contracts.mdAFPS sequence, completed task summaries, known routing and alignment-gate fixes.
Subscription pricingOpenAI ChatGPT Pro help, ChatGPT pricing, Anthropic Claude Max helpCost range only; no personal billing record was available.

Explicit evidence is separated from inference below. The most important inference is the subscription spend range: the logs prove usage, not actual billing tier or renewal timing.

Evidence Coverage Gate

Is the evidence coverage sufficient for a cost-vs-progress operating assessment?

Overview Stats

MetricPre-windowAFPS windowInterpretation
Date range2026-05-15 23:58 ET to 2026-05-22 20:58 ET2026-05-22 20:58 ET to 2026-05-29 17:58 ETSame 6.875-day span.
User prompts47588AFPS period had much higher interactive steering.
Sessions16235More work split across focused sessions and runners.
Claude prompts32415Claude remained the dominant interactive surface.
Codex prompts16173Codex was materially used, especially for analysis and implementation handoffs.
Git commits in repo276121Raw commit count fell after the benchmark sprint; this is not a pure progress loss.
Unique paths touched5622,065Post-AFPS touched a wider system surface, mostly due pack and skill contract restructuring.
Added benchmark files1392Pre-window was benchmark-output heavy; post-window shifted away from report churn.
Added test files29Post-window added more focused regression coverage.
Added alignment files66Alignment review remained a steady workflow primitive.
Logged token events32.7M458.6MIncludes cached context; useful as a utilization signal, not billing cost.

Top post-AFPS projects by prompt volume: agentic-skills 256, content 131, calcllm 61, gblock-party-redux 60, projects 31.

Top post-AFPS commands: /clear 59, /resume 16, /pack 16, /ship-end 13, /provision-agentic-config 12, $analyze-sessions 8, /investigate 7, $investigate 7, $run 7.

Cost Frame

Pricing was checked against official sources during this run. OpenAI documents ChatGPT Pro as a $200 Pro plan. Anthropic documents Claude Max web subscriptions as two tiers: $100/month for Max 5x and $200/month for Max 20x. Because the local logs do not reveal your exact Claude Max tier, this report uses a range.

AssumptionMonthly spendProrated 6.875-day spendPost-AFPS progress ratios
ChatGPT Pro + Claude Max 5x$300/monthabout $68.758.6 prompts per dollar; 1.8 commits per dollar; 6.7M logged token-events per dollar.
ChatGPT Pro + Claude Max 20x$400/monthabout $91.666.4 prompts per dollar; 1.3 commits per dollar; 5.0M logged token-events per dollar.

The better measure is not commits per dollar. It is whether subscription access produced durable operating assets: canonical AFPS routing, alignment gates, tests, install fixes, progress reports, product showcase improvements, and content/devrel planning. On that lens, the spend looks productive, but still not financially recouped.

Codex utilization caveat: all post-AFPS Codex token-count events with plan metadata reported plan_type: pro. The highest observed Codex primary-window usage was 7%, and the highest observed weekly usage was 18%. That means Codex Pro was used, but not exhausted.

Progress Evidence

Durable progress produced after AFPS adoption

Control and deliberation signals

Categorized Patterns

PatternCountReal examplesInterpretation
Workflow/skill-system work193 promptskeep it to AFPS; based on our afps workflow, do you see any other routing issues?AFPS became an explicit operating contract, not a vague preference.
Product/showcase work155 promptscan we amend the front end website showcasing the new alignment-first, prototype second skills workflow?The workflow turned into a product/devrel surface, not only internal process.
Analysis/review work81 prompts$analyze-sessions ... how the new alignment first...; $investigate ... benchmark failures?More time spent checking the system's behavior before pushing onward.
Shipping/validation work55 prompts/ship-end, validation caveat notes, benchmark and test prompts.The workflow repeatedly closed loops with validation and commits.
Bug/friction work44 promptsjourney map skill ... doesn't route properly; value-prop-canvas was recommended before positioning?AFPS exposed routing drift. This is painful but useful because it generated durable fixes.
Explicit AFPS markers26 promptsnew alignment-first, prototype-second skills workflow; AFPS workflowThe new language is established enough to guide corrections and content planning.
Context reset/resume overhead84 prompt patterns/clear 59, /resume 16, prior-agent plan prompts 9.High usage came with context-management overhead. This is the clearest remaining efficiency gap.

Skill Performance Trends

Skill or workflow surfaceEvidencePerformance read
analyze-sessions8 post-AFPS Codex invocations plus Claude usage; generated prior reports such as pack install issues and split-path analysis.Useful for broad pattern detection. It should not become the default answer for every single incident.
investigate / session-triageAt least 14 visible post-AFPS investigate invocations across Claude/Codex, plus specific route and benchmark incidents.Effective at turning friction into verified fixes. The journey-map and codebase-status fixes are good examples.
AFPS business/product skillsPrompts flagged journey-map, positioning, value-prop-canvas, research-roadmap, and codebase-status route drift.The concept is strong, but route contracts required repeated hardening. Current state is better than initial AFPS state.
pack / install/discovery workflow/pack 16 post-AFPS prompts; separate pack install issues analysis and launcher/discovery commits.Still high-friction, but multiple root causes were closed: stale symlink installs, launcher root resolution, and missing fallback guidance.
Alignment-page conventionSix added alignment files in both pre and post windows; broad commits for inline questions, section feedback, dark mode, and archived replacement behavior.Strong progress toward deliberate review. The cost is extra ceremony and extra browser/open/handoff friction.

Evidence Matrix

ClaimEvidenceInferenceConfidenceAssumption statusDecision impact
AFPS has been adopted as a real operating frame.First explicit marker on 2026-05-22 20:58 ET: /series-spec ... new alignment-first, prototype-second skills workflow. Total explicit AFPS markers: 26.The acronym and sequence are now repeatedly used to judge skill outputs.HighEvidence-backed.Keep AFPS as the default product workflow unless future product evidence contradicts it.
Operating progress increased, but raw commit count did not.AFPS window: 121 commits, 2,065 unique paths, 162,049 additions, 51,378 deletions. Pre-window: 276 commits, 562 unique paths.Post-AFPS work was broader and more structural; pre-window had more small benchmark/report commits.HighEvidence-backed for repo activity; progress quality is interpreted.Judge AFPS on durable capability, not commit count alone.
The spend was productive but not financially returned.Estimated subscription spend for window: $69-$92. No revenue artifact was found or provided.Financial ROI is negative; workflow asset return is positive.MediumBilling tier and revenue are unverified.Use operating ROI language, not financial ROI language.
Claude was the primary working surface.Post-AFPS compact history: 415 Claude prompts vs 173 Codex prompts.Claude carried most interactive steering; Codex supplemented analysis and implementation.HighEvidence-backed.Use Codex more deliberately if the goal is to maximize ChatGPT Pro.
Codex Pro had headroom.Codex rich logs reported plan_type: pro, max primary usage 7%, max weekly usage 18%.The Pro subscription was used but not saturated in this window.HighEvidence-backed for logged sessions only.Shift batch analyses, validation, and report generation to Codex when appropriate.
AFPS improved deliberation but surfaced drift.81 analysis/review prompts, 44 bug/friction prompts, route corrections around journey-map/value-prop/codebase-status.More controlled work also means more visible contract defects.HighEvidence-backed counts; qualitative interpretation.Preserve friction as test cases rather than treating it as wasted effort.

Research Completeness Gate

Which evidence-backed claim needs more support before you would rely on this report?

Confidence And Assumption Register

ItemStatusConfidenceWhat would change it?
AFPS start boundaryFirst explicit history marker used as boundary.HighA user-provided earlier private adoption marker.
Prompt/session countsCompact histories parsed fully.HighHidden/deleted history outside local files.
Token utilizationRich Claude and Codex logs parsed; cached tokens included.MediumProvider billing/usage dashboards or filtered duplicate corrections.
Subscription spendEstimated from official current pricing range.MediumYour exact Claude Max tier and billing dates.
Progress qualityInferred from commits, task summaries, route fixes, tests, and durable artifacts.MediumA scored artifact ledger or user-weighted value rubric.
Financial ROINo revenue evidence in scoped local artifacts.MediumRevenue, leads, subscriber growth, or deal evidence tied to AFPS outputs.

Assumptions Gate

Which assumption should be corrected first?

Ranked Recommendations

RankPatternFrequencyRecommendation typeSuggested shape
1Context reset/resume overhead59 /clear, 16 /resume, 9 prior-agent plan promptsSkill or standing instructionUse a concise AFPS resumption packet that carries current phase, active path, last validation, and next allowed route.
2Codex Pro headroomMax weekly usage 18%Operating habitRoute batch report generation, broad history analysis, and validation-only checks to Codex when not blocked by UX or Claude-specific tools.
3AFPS route drift44 friction prompts; multiple route-fix commitsContract testsKeep focused route tests for every changed AFPS skill and audit downstream recommendations after each route change.
4Progress/cost ambiguityThis analysis had to reconstruct cost from logsSkill/reportMaintain a lightweight weekly AFPS operating ledger: spend assumption, prompts, sessions, commits, artifacts, validation, revenue/leads.
5Alignment ceremony costSteady alignment artifact production plus browser-open frictionWorkflow polishKeep alignment pages, but improve review answer ingestion so YAML feedback becomes follow-up work without manual re-interpretation.

Highest-impact automations by avoided manual prompts

Alternatives, Lower-Confidence Findings, And Gaps

Alternatives considered

Source gaps

Scope Gate

Should this report stay as an operating assessment, or should it be expanded into a stricter ROI/accounting analysis?

Proposed File Changes

This report-only run proposes one durable file:

No task files, skill files, tests, or workflow docs are changed by this report. The existing dirty tasks/todo.md expert-review additions were preserved untouched.

Proposed File Changes Gate

Is the proposed report artifact acceptable?

Post-Approval Gate

After reviewing this report, what should happen with the findings?

Compile Answers

Answer every required gate question above, then compile the review payload. The YAML includes required gate answers and any optional section feedback you selected.