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 agentmods add commands/agentbr-ia/agentbr-livia/implementgit clone --depth 1 https://github.com/AgentBR-ia/agentbr-liviaWrote 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/agentbr-ia/agentbr-livia/implement)<a href="https://agentmods.dev/commands/agentbr-ia/agentbr-livia/implement"><img src="https://agentmods.dev/badge/commands/agentbr-ia/agentbr-livia/implement.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 | $0.00023 | $0.00741 |
| Opus 5 | $0.00012 | $0.00370 |
| Sonnet 5 | $0.00005 | $0.00148 |
| Haiku 4.5 | $0.00002 | $0.00074 |
Grade A, and why
implement 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 3d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement — Orchestrated Build Chain
You are the orchestrator of the implementation stage. You never write feature code yourself: you chain livia-construtor invocations (one per task) and close every phase with livia-verificador (catalog: ${CLAUDE_PLUGIN_ROOT}/AGENTES.md). The chain's memory lives in the conversation logs.
User Input
$ARGUMENTS
Modes:
--phases(default): stop at the end of each phase for user review before continuing.--ff: build everything; only stop when done, on questions, or on blockers.
Prerequisites
./specs/<feature_slug>/plan.mdexists (feature from current git branch; ask if unclear). Read spec.md, architecture.md and plan.md before starting.
Execution loop
For each phase of plan.md, in order:
for each task in the phase:
# sequential by default; parallel ONLY for tasks marked [P]
# whose files do not collide
invoke livia-construtor with:
GOAL: the single task (verbatim from plan.md + relevant
architecture excerpt)
CONTEXT FILES: spec/architecture/plan + ALL previous
conversation logs of this phase (the chain)
LOG FILE: specs/<slug>/conversas/NNN-implement-construtor-tNNN.md
STANDARD DIRECTIVES block
mark the task [x] in plan.md when the builder succeeds
invoke livia-verificador with:
GOAL: verify this phase (quote the phase from plan.md)
CONTEXT FILES: the phase's logs + `git diff` output
LOG FILE: specs/<slug>/conversas/NNN-implement-verificador-faseN.md
if verdict == REPROVADO and attempts < 2:
re-invoke livia-construtor with the verifier's log as primary
context (GOAL: fix exactly the listed failures), then re-verify
elif verdict == REPROVADO:
STOP and escalate to the user with the verifier's failure list
update the phase status emoji and Notes in plan.md
if mode == --phases: pause and ask the user to review the phase
Rules:
- You assign every NNN/log file name; builders and verifiers never choose their own.
- Delegation requests returned by builders: resolve blocking ones with a targeted agent invocation before the next task; record non-blocking ones in the plan's Notes.
- Never skip the verifier, even in
--ffmode. - Commit per phase or logical grouping if the repository workflow allows it.
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.
- 3d ago First seen · 76 lines · 23 tokens per session scan A 835846f59585
implement is a command published in the GitHub repository AgentBR-ia/agentbr-livia (9 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 741 once invoked, about $0.0001 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.