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/jabrena/plinth/implement-specgit clone --depth 1 https://github.com/jabrena/plinthWhat 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 | $0.00012 | $0.02321 |
| Opus 5 | $0.00006 | $0.01161 |
| Sonnet 5 | $0.00002 | $0.00464 |
| Haiku 4.5 | $0.00001 | $0.00232 |
Grade A, and why
implement-spec 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 yesterday.
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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
implement-spec
Deliver an approved implementation plan or validated OpenSpec task list through controlled implementation.
Usage
/implement-spec <approved-plan|openspec-change> [task-or-group] [constraints]
Accepted inputs
- An approved implementation plan (
*.plan.md) - An OpenSpec change containing a validated
tasks.md - Optional task or group selection, branch/worktree context, and implementation constraints
A bare issue is context, not an execution contract. When repository policy requires structured planning and neither executable artifact exists, stop and direct the user to provide an approved implementation plan or run /create-spec.
Owner and delegation
- Owner:
@plinth-tech-lead - Delegation targets:
@plinth-java-coder,@plinth-java-spring-boot-coder,@plinth-java-quarkus-coder,@plinth-java-micronaut-coder, or@plinth-no-java - The tech lead coordinates delivery and MUST NOT implement application code directly.
Mandatory execution contract
- If the command runner is not
@plinth-tech-lead, immediately delegate the whole command execution to@plinth-tech-leadand wait for its result. @plinth-tech-leadMUST invoke the selected implementation agent for implementation, test, and verification work; naming an agent in the response is not delegation.- If agent invocation is unavailable in the current environment, stop and report that
/implement-speccannot proceed instead of implementing directly. - For OpenSpec inputs, pass the OpenSpec readiness gate below before skill discovery, Git-location changes, or implementation delegation.
- Before any implementation agent starts, pass the branch/worktree gate below and report the selected isolation strategy.
- Before any implementation agent starts,
@plinth-tech-leadMUST publish a Skill discovery brief and pass an ordered candidate skills to read list in every implementation handoff.
OpenSpec readiness gate
- After loading and structurally validating the selected change, determine the selected execution scope from the requested task or group, or all incomplete tasks when no narrower scope is supplied.
- Require bidirectional traceability: every selected behavior-changing implementation task has one or more concrete scenarios in
specs/**/spec.md, and every scenario applicable to the selected scope has an actionable implementation or verification task. Repository validation tasks must map to an explicit quality, safeguard, or verification obligation. - A concrete scenario defines its trigger, required preconditions, and observable outcome without unresolved placeholders. An actionable task names a specific remaining implementation or verification outcome; completed-only tasks do not provide executable work.
- Treat evidence as not ready when it is absent, ambiguous, placeholder, completed-only, partial, or divergent from the selected change requirements or safeguards.
- When the gate fails, stop and report each unsupported scenario or task, identify the owning OpenSpec artifact, and instruct the contributor to update the OpenSpec change and rerun
/implement-spec. - The command must not invent acceptance criteria or tasks. A failed readiness gate stops before skill discovery, Git-location changes, or implementation delegation.
- Do not require unrelated future task groups to be implementation-complete when a narrower task or group was explicitly selected.
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.
- yesterday First seen · 142 lines · 12 tokens per session scan A 7f128abf3a32
implement-spec is a command published in the GitHub repository jabrena/plinth (435 stars, last pushed today), licensed Apache-2.0. It adds 12 tokens to every session and 2,321 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 2026-08-30.
Other commands, from other repositories
ai-do
You are a routing assistant for DSPy AI skills. Understand the user's problem, pick the best skill, and generate a ready-to-run prompt.
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.