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.
git clone --depth 1 https://github.com/bovinphang/frontend-craftWrote 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/commands/bovinphang/frontend-craft/fec-plan)<a href="https://agentmods.dev/commands/bovinphang/frontend-craft/fec-plan"><img src="https://agentmods.dev/badge/commands/bovinphang/frontend-craft/fec-plan.svg" alt="Measured on agentmods" 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 | $0.00052 | $0.00945 |
| Opus 5 | $0.00026 | $0.00473 |
| Sonnet 5 | $0.00010 | $0.00189 |
| Haiku 4.5 | $0.00005 | $0.00094 |
Grade A, and why
fec-plan 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 7d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create a front-end plan before changing the code. Automatically divert traffic to implementation planning or test planning based on user intent.
Intent recognition
- Implementation Planning (default): Users need to dismantle components, design data flows, arrange directory structures, migration steps, and architecture plans.
- Test Planning: The user clearly states "test plan", "test strategy", "coverage matrix", "test layering", "what to test", "risk-to-test", etc.
- Mixed: Users have both implementation and testing requirements.
If the intention is unclear, first ask the user if they want to see the implementation plan or test strategy.
Implementation planning path
- Restate user goals, success criteria, and out-of-scope content.
- Read relevant codes, templates, rules, configurations, tests and existing implementations to avoid deviating from the current status of the project.
- If it involves page splitting, state flow, directory structure, data flow or large-scale reconstruction, entrust
fec-architect. - Output plan:
- Scope of influence
- Key files or modules
- Architecture and module boundaries
- Data flow/state flow/API interaction
- Implementation phase
- Rollback or gradual migration strategy
- Risks and Mitigation
- Minimal verification access (lint, type-check, test, build, E2E or manual acceptance)
- For decisions related to version sensitivity, dependency upgrades or external libraries, list the source of fact, version range, migration impact and documents that need to be verified.
- Implementation is not performed until user confirmation.
The implementation plan is saved to reports/architecture-proposal-YYYY-MM-DD-HHmmss.md.
Test planning path
- Determine the scope:
- When users specify functions, PRs, files or business processes, this scope shall prevail.
- When not specified by the user, view recent changes and infer the main risk areas.
- If the user wants module splitting, state flow, directory structure or migration steps, return to the implementation planning path.
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.
- 7d ago First seen · 94 lines · 52 tokens per session scan A 9abd6b5671cc
fec-plan is a command published in the GitHub repository bovinphang/frontend-craft (21 stars, last pushed 5d ago), licensed MIT. It adds 52 tokens to every session and 945 once invoked, about $0.0003 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 2026-08-30.
Other commands, from other repositories
gen-evals
Generate EVAL-.md test cases for an agent from its prompt. Usage: /gen-evals [--count N].
prompt-evolve
Closed prompt-evolution loop: turn a lesson into a candidate agent prompt, gate it on held-out evals, promote only if it beats the baseline. SIA Meta→Target→Feedback ported to greatcto.
octo-deliver
Delivery phase - Review, validate, and test with multi-AI quality assurance.
review
12-angle code review + skeptical triage (3-round + arbiter) for security/reliability P0/P1 findings, OR traceability tree. Default: review current branch vs main. --deep: triage ALL P0/P1 angles (not just security). With trace : render REQ → IMPL → TEST tree for impact analysis. Creates or closes gate:code for…
voice-compliance
Voice/telephony compliance check — invokes voice-ai-reviewer to produce TM-voice-{slug}.md with TCPA, STIR/SHAKEN, state recording-consent, EU AI Act Art. 50, and synth-voice deepfake-law gaps.
test
Run the repository's actual test suite: every ecosystem's canonical runner — NOT run is never green.