AI-workflow generator · v0.20.0 · MIT

An AI‑workflow generator that publishes its own report card.

It reads your codebase and forges a project-specific workflow — rules, skills, commands, agents, MCP config, memory — then measures the pieces it ships against a pre-registered harness and commits the raw scores, weak grades included.

claude plugin marketplace add directiveforge/directiveforge
claude plugin install directiveforge
View the source on GitHub MIT-licensed · a Claude Code plugin

The re-measure

inversion · activation repeatability
0.3333 0.8333 n=30
Wilson 95% CI · decision pack F → B band · CIs do not overlap l1/decision/scorecard.md

The proof, up front

Read the report card before you read the pitch.

Every row below traces to a committed artifact that ships in the repo. Open it and check. These are the metrics that carried an F at baseline, re-measured after the fix.

Scores — higher is better · 0 to 1.0

inversion trigger F1
improvement
0.3333 0.75 point estimate · no CI
l1/decision/scorecard.md

v1.0 single-call channel, same instrument as baseline

inversion activation repeatability
improvement
0.3333 0.8333  [0.6644, 0.9266] n=30
l1/decision/scorecard.md

Wilson 95% CIs do not overlap

anti-sycophancy-meta trigger F1
improvement
0.5714 0.8889 point estimate · no CI
l1/decision/scorecard.md

v1.0 channel

anti-sycophancy-meta activation repeatability
improvement
0.2667 0.8333  [0.6644, 0.9266] n=30
l1/decision/scorecard.md

CIs do not overlap

name-generation trigger F1
improvement
0.8889 1.0 point estimate · no CI
l1/naming/scorecard.md

v1.1 batched channel + equivalence block

brownfield-api planted-signal recall
improvement
0.90 1.00 point estimate · no CI
brownfield-api/l2.2-signals.md

10/10; Heroku trap now a correctly-flagged negative

Defects — removed

brownfield-api false-content count
removed

all 4 planted traps now cited only with a drift flag

brownfield-docs destructive-action count
removed

backup + audit-trail manifest; the hard F-cap lifts

brownfield-docs link-gate false positives
removed

same 2 real dead links kept (exit 1); 13 FP → 0

On the measured slice: decision pack F B band brownfield-api F A band brownfield-docs F-cap lifted

derivation & scope — DELTA.md

Regressions ship too

The row that costs us, in the same table as the wins.

disconfirming-evidence-first trigger F1
regression
0.9091 0.8889 point estimate · no CI
l1/decision/scorecard.md

the boundary rewrite that killed a poem false-positive also lost a tone-check positive — a real trade, filed

We publish the row that costs us, because a report card that only shows the good numbers is marketing.

Measured, not claimed

The harness is pre-registered.

The measurement spec is committed to git before any run — a release verifier checks in history that the spec’s first commit predates the first results commit, so metrics can never be redefined after seeing the numbers. Every figure carries its n, its method, and a 95% CI — or an explicit “single-run, directional” caveat. A number that cannot be recomputed from a committed raw artifact does not ship.

A Fable-5 blind re-judge agreed with the rubric judge on 18/20 scores exactly (0.90) and 20/20 within ±1 (1.00).

What it is

A generator with a proof harness.

A generator, not a catalog
It reads your codebase and synthesizes a workflow for your stack and conventions — not a pile of prebuilt components to pick from.
22 measured skills
Across three packs — decision (12), naming (6), design-elevation (4) — each with trigger and activation numbers in the harness results, not just prose.
A proof harness
It scores the generator on itself: artifact-level statistical scoring (trigger F1, activation repeatability with CIs, anchored rubrics) plus an end-to-end benchmark on synthetic fixture repos with answer keys.
A vigilance loop
It scans the AI ecosystem daily, synthesizes weekly, and integrates monthly — so the kit’s knowledge does not silently rot as models and frameworks move.

What it is not

And what it refuses to be.

Not a CLI or a SaaS
There is no binary and no server. The plugin installs skills; the generator is a prompt you paste; upgrades run through a manifest.
Not a 200-skill catalog
22 skills, each with a published trigger score. Breadth is not the pitch; measurement is.
Not infrastructure benchmarks
No latency, RSS, or throughput numbers. The harness measures workflow-artifact quality and generator behavior on fixtures — a different axis entirely.
Not autonomous
The generator asks before it writes. Upgrade mode dry-runs by default. /report-friction never submits anything without your explicit review. Nothing edits your repo behind your back.
Not self-congratulatory
The baseline published F grades. The numbers are recorded before they are fixed, and the regressions ship in the same table as the wins.

60-second quickstart

Three steps to a measured workflow.

  1. Install the skills and commands as a plugin

    Two commands. This installs the 22 measured skills (decision / naming / design packs) and the workflow commands, including /report-friction.

    claude plugin marketplace add directiveforge/directiveforge
    claude plugin install directiveforge
  2. Generate a project-specific workflow

    Open a session at the root of your target project and paste generator/PROJECT_SETUP_PROMPT.md. It reads your codebase, asks a short profile, and writes your CLAUDE.md, .cursor/rules/*.mdc, .claude/commands/, agents, and MCP config.

    generator/PROJECT_SETUP_PROMPT.md
  3. Cursor consumes skills as files

    Copy templates/skills/<pack>/ into your project per the Cursor workflow.

    workflows/WORKFLOW-CURSOR.md

Full walkthrough: QUICK_START.md

Honest limitations

Where the numbers stop.

None are softened; each links to where it lives in the repo.

Not everything was re-measured
The delta re-ran only the metrics that carried an F. Static gates (L1.1) and rubric scores (L1.4) were not re-measured post-fix; the greenfield fixture was deferred to public round 2. Absent, not zero. DELTA.md
Single-run directionality
Layer 2 and some claim rows are single re-measure runs. Where a metric is not CI’d, it is labelled directional, not proven.
The self-checklist is our own instrument
The L2.1 checklist measures self-consistency, not external quality — circular by construction. The answer-key-scored metrics (L2.2 / L2.4 / L2.6) are the external check.
Judge-model dependence
Trigger routing is simulated with Haiku and rubric scores are judged by Opus — both are LLM judges. A Fable-5 blind re-judge calibrates the rubric judge, but a different judge could move borderline rows. calibration-fable.md
Synthetic-fixture boundary
Layer 2 runs against synthetic reference repos with answer keys, not real projects. We make no claim that the kit improves real-project outcomes. Nobody in the ecosystem measures that yet — including us.
A regression shipped this release
disconfirming-evidence-first F1 0.9091 → 0.8889, disclosed above and filed for the next patch. Six residual defects are open and dispositioned. feedback/DISPOSITIONS-v0.19.0.md

Freshness

Knowledge rots silently. The cadence is public.

Scan / synthesize / integrate
A daily scan of a severity-tagged watchlist, a weekly synthesis that separates signal from noise, and a monthly integration through a reviewed session — never an auto-merge. workflows/KIT-VIGILANCE.md
A weekly public digest
What moved upstream, what it means for kit users, what shipped or is queued, and the open friction-report count with disposition status — on GitHub Releases. vigilance/PUBLIC-DIGEST-FORMAT.md

Feedback

Every report answered. Zero silent drops.

/report-friction
Harvests the defect (file:line, expected vs actual, severity), sanitizes paths and names, and stops at a review gate. Nothing is submitted until you approve it.
The disposition guarantee
Every report is answered in a public DISPOSITIONS file — fixed, deferred-with-reason, or rejected-with-reason. feedback/DISPOSITIONS-v0.19.0.md

For the skeptic

The questions a Hacker News reader asks first.

Is this a SaaS or a CLI I have to run?

Neither. There is no binary and no server. The plugin installs skills into Claude Code; the generator is a prompt you paste at your project root; upgrades run through a manifest. Nothing phones home.

Does it actually improve my real project?

We make no such claim. The harness measures generator behavior on synthetic fixture repos with answer keys — not real-project outcomes. Nobody in the ecosystem measures that yet, including us. What we publish is what we can recompute from a committed artifact.

What is a pre-registered harness?

The measurement spec is committed to git before any run. A release verifier checks in git history that the spec’s first commit predates the first results commit, so metrics cannot be redefined after seeing the numbers. Tuning a rubric to pass is a spec change, a new dated version, and a re-run — not a quiet edit.

Why publish your own F grades and a regression?

Because a report card that only shows the good numbers is marketing. The baseline F grades and the shipped regression sit in the same table as the wins — that is the credibility mechanism, not a footnote.

The F grades ship in the same table as the wins.

claude plugin marketplace add directiveforge/directiveforge
claude plugin install directiveforge

Free · MIT · open source · github.com/directiveforge/directiveforge ↗