Which agents work with it?

Any agent that reads skills from a directory. Claude Code, Codex, Antigravity CLI and Grok Build all read /present natively.

What does “free and unlimited” mean?

Generating presentations is free with no cap. Narration runs on your own machine, so there's nothing to meter.

Where does the narration run?

On your machine. The finished presentation publishes to your channel so anyone with the link can watch it.

Do I have to write slides?

You never touch slides. You ask — “brief me on what shipped overnight” — and your agent authors, narrates, and publishes.

Every presentation gets a watch link on your channel. Send the link; it plays in any browser, phones included.

Yes — the /present skill is MIT-licensed, and the authoring spec is public.

ECC's module-regression skill reruns everything downstream of the module you changed

github.com/affaan-m/ECCmerged Oct 11, 2026

module 03: PASS

05-aggregation · exit 1

github.com/affaan-m/ECC/pull/3413 · skills/module-regression/SKILL.md

The ECC plugin added a skill called module-regression. After a change, it runs the module you touched and every module that depends on it. If any of them fails, your change is not done.

Agents check the module they changed and miss the one it broke

github.com/affaan-m/ECCmodule-regression · PR #3413

Modifying A may break B.

The defect appears days later, when an aggregate, export, or external behavior is wrong.

skills/module-regression/SKILL.md · Problem

In a large repository, modules depend on each other. People and agents tend to verify only the module they changed. So a downstream consumer fails silently, and a wrong total or export turns up days later.

A ledger names each module's consumers and the command that proves it works

github.com/affaan-m/ECCREGRESSION.md

## Module 03: Shop Data Cleaning

Downstream consumers: 05-aggregation, 07-final-export

Acceptance command: pytest tests/test_03.py && python scripts/reconcile.py --module 03

Propagation rule: external behavior change → run 05 and 07

skills/module-regression/SKILL.md · Three Required Fields per Module

The skill keeps that map in a file called REGRESSION.md. Each module lists its downstream consumers, a command that proves it still works, and a rule for which consumers must rerun after a change.

Consumers come from the dependency graph, never from a guess

github.com/affaan-m/ECCmodule-regression · PR #3413

build tooling or import scanrecorded edge

edge it cannot establishunverified · blocks all-green

skills/module-regression/SKILL.md · Three Required Fields per Module

The consumer lists come from the repository's build tooling or a reproducible import scan. An edge the scan cannot establish is marked unverified, and an affected unverified edge blocks an all-green result until a person confirms it.

The verdict is the exit code, not a model's review

github.com/affaan-m/ECCmodule-regression · Four Invariants

no acceptance commandledger gap, not a pass

one red downstream consumerchange unfinished

auditorreports, does not fix

skills/module-regression/SKILL.md · Four Invariants

The verdict is the exit code, not a model looking and finding no problem. A module with no acceptance command is a gap, never a pass. One red consumer means the change is unfinished, and the author fixes it.

Ledger commands are shown for review before they run

github.com/affaan-m/ECCmodule-regression · Audit Flow

# .agents/skills/module-regression/agents/openai.yaml

policy:

allow_implicit_invocation: false

skills/module-regression/SKILL.md · Audit Flow · agents/openai.yaml

Ledger commands count as untrusted repository content. The skill lists them with their risks, timeout and network needs, and asks before any new authority. Codex runs it only when you call it by name.

test-collaboration ties each requirement and bug to a TEST-ID

github.com/affaan-m/ECCtest-collaboration · PR #3413

TEST-ORDER-001

state: missing · in progress · unverified · covered · not applicable

source: requirement, rule, risk, bug or incident

A bug fix without a TEST-ID or a recorded manual exit is not closed.

skills/test-collaboration/SKILL.md · sections 2 and 3

The companion skill, test-collaboration, gives each requirement, business rule and bug a stable test ID with a state. A bug fix with no test ID, and no recorded manual check, does not count as closed.

Covered means a passing command and assertions on behavior

github.com/affaan-m/ECCtest-collaboration · section 5

command exit code0

asserts only “called” or HTTP 200not covered

test count or green CI alonenot covered

skills/test-collaboration/SKILL.md · Review Test Evidence

A test ID is marked covered only when its command exits zero and its assertions check behavior. A test that only confirms a call happened, or got an HTTP 200, does not count, and neither does a green CI run.

Separate green client and server tests do not prove they agree

github.com/affaan-m/ECCtest-collaboration · section 4

contractschema lint

consumergenerated mocks

providerserialized response

integrationone real path

skills/test-collaboration/SKILL.md · Drive Cross-Boundary Tests from One Contract

When a frontend and backend are built apart, one machine-readable contract feeds the contract, consumer and provider tests. One test ID also needs a real cross-boundary path, or a recorded gap.

One optional install module, in beta and off by default

github.com/affaan-m/ECCmanifests/install-modules.json

documentation-test-regressionbeta

defaultInstallfalse

targets14 harnesses, incl. Claude Code, Codex, Cursor, OpenCode

github.com/affaan-m/ECC/pull/3413 · manifests/install-modules.json · install-profiles.json

Both skills ship together as one optional install module, marked beta and off by default. Only the full profile includes it. It targets fourteen harnesses, among them Claude Code, Codex, Cursor and OpenCode.