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.
npx skills add cielebak/goal-by-goal --skill gbggit clone --depth 1 https://github.com/cielebak/goal-by-goalWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/cielebak/goal-by-goal/gbg)<a href="https://agentmods.dev/skills/cielebak/goal-by-goal/gbg"><img src="https://agentmods.dev/badge/skills/cielebak/goal-by-goal/gbg/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/cielebak/goal-by-goal/gbg"><img src="https://agentmods.dev/badge/skills/cielebak/goal-by-goal/gbg.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00150 | $0.02574 |
| Opus 5 | $0.00075 | $0.01287 |
| Sonnet 5 | $0.00030 | $0.00515 |
| Haiku 4.5 | $0.00015 | $0.00257 |
Grade A, and why
gbg 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal-by-Goal Plan
Convert an unstructured plan, PRD, or conversation context into a goal-by-goal execution document with a strict reviewer gate between goals. Implementation agent (Claude) executes one goal at a time. Reviewer agent (Codex / human senior) reviews read-only after each goal. Commit only on PASS.
When to use
- Building a feature that splits into a few independently shippable steps
- Greenfield MVPs that decompose into 5–12 reviewable milestones
- Multi-week migrations (platform parity, framework upgrades, stack swaps)
- Large refactors with clear surface area
- Security hardening / compliance work
- Any development where "did we actually do it correctly?" needs a second pair of eyes between commits
When NOT to use
- One-shot bugfixes
- Exploratory spikes without success criteria
- Pure design exploration
- Trivial single-file changes
Process
1. Locate the source plan
Ask user where the plan lives. Accept any of:
- A PRD file path
- A GitHub issue URL (
gh issue view <n> --comments) - A conversation summary in chat
- A bullet list
If unclear, ask: "Where does the plan live, or should I draft it from this conversation?"
2. Gather project parameters
Ask user (one block, not one-by-one):
- Project scope name (kebab-case, used in paths and commit scope). E.g.
android-parity,react-to-solid,auth-hardening. - Reviewer — ask the user, present Codex as the default and recommended
choice. Offer Claude as a second option, and let them type anything else
(GPT / human senior / multi-reviewer) by hand. The choice drives how
the review gate runs:
- Codex (or any CLI reviewer) → the generated
scripts/gbg-review.shwrapper (codex exec --sandbox read-only). - Claude → spawn a read-only review Agent/Task with the reviewer prompt;
save its verdict to the same
docs/<scope>/reviews/goal-XX-<reviewer>.md. - Anything else → run the reviewer manually with the prompt; save the verdict to the same path.
- Codex (or any CLI reviewer) → the generated
- Required checks — exact bash commands per platform (build, test, lint). E.g.
./gradlew :app:assembleDebug,xcodebuild test ...,npm test. - Locked decisions — things the user does NOT want re-litigated mid-execution (stack choices, scope boundaries, out-of-scope items).
- Current state summary — known issues, gaps, anything pre-existing.
- Language — copy in PL or EN? (Default EN for code/docs, PL for user-facing strings if iOS/Android app.)
- Target goal count — 5–12 typical. Default 8.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 214 lines · 150 tokens per session scan A 0f7deb4efa59
gbg is a skill published in the GitHub repository cielebak/goal-by-goal (1 stars, last pushed 2mo ago), licensed MIT. It adds 150 tokens to every session and 2,574 once invoked, about $0.0007 per session on Opus 5. 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 2026-08-31.
Other skills, from other repositories
setup
A project-initialization workflow for creating a new Workframe project or connecting an existing project to Workframe.
material-intake
A planning tool for sorting existing project files into a suitable structure and suggesting a basic and submodule tree. It inventories files, recommends where each group should go, and produces a plan without moving anything.
code-review
A code-review skill that examines changes for requirement fit, correctness, security, maintainability, and performance. It reports findings with risk levels.
feature-breakdown
A guide for breaking a large request into an epic, user stories, and smaller tasks. An epic is a broad goal, a user story describes one independently useful outcome, and a task is a concrete piece of work.
html-demo
A workflow for building a self-contained interactive HTML demo from a screenshot and a short requirement. The demo imitates the interface and includes simulated controls so its states can be explored.
product-metrics-design
A method for designing a product measurement system using frameworks such as AARRR, HEART, North Star, and OKR. It organizes measurements into a main outcome, supporting drivers, and guardrails that prevent harmful trade-offs.