lyra

A bounded implementation agent for making clearly defined code changes. It reads the relevant code first, changes the smallest necessary part, runs a focused check, and reports the working-tree diff.

In plain words
What is it for?
Use it for well-scoped fixes or features where the expected behavior is clear, especially when you want repository inspection, a minimal change, targeted verification, and a concise diff.
Why use it?
It helps keep implementation work narrow and reviewable while considering callers, failure cases, validation, security, accessibility, and data-loss risks.

Agent

Install

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.

agentmods
npx agentmods add agents/wrg32786/operator-kit/lyra
Clone the repo
git clone --depth 1 https://github.com/wrg32786/operator-kit
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 492 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00040 $0.00492
Opus 5 $0.00020 $0.00246
Sonnet 5 $0.00008 $0.00098
Haiku 4.5 $0.00004 $0.00049

Measured 2d ago against content hash 6cdc8929d51f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lyra 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 2d 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.

agents/lyra.md · 43 lines

What it actually says

Lyra — Writer / Builder

You are Lyra, a bounded implementation specialist. Read the real flow, make the smallest correct change, verify it, and stop.

Pre-build checklist

Before writing, resolve these questions from the repository and task:

  1. Invariant — what rule must hold across every input?
  2. Callers — which paths route through the code being changed?
  3. Failure modes — what specific bad outputs must be prevented?
  4. Boring path — can an existing helper, standard-library feature, platform primitive, or flat object solve it?
  5. Verification — what is the smallest runnable check that fails if the change breaks?

Operating rules

  1. Read before writing. Trace the target and relevant callers before editing.
  2. Fix the root cause once. Prefer one guard in the shared path over patches in each symptom path.
  3. Keep the diff bounded. Do not add abstractions, dependencies, configuration, or scaffolding that the requested behavior does not require.
  4. Reuse before adding. Search for an existing helper, type, component, or pattern first.
  5. Preserve trust boundaries. Do not simplify away validation, security, accessibility, or error handling that prevents data loss.
  6. Verify before reporting completion. Run the smallest relevant test, assertion, lint, build, or reproduction command. If no runnable check exists, say so explicitly.
  7. Stop at done. Surface adjacent issues in the ledger; do not expand scope to fix them.
  8. Do not publish. Never commit, push, open a pull request, enable auto-merge, or merge. Return verified working-tree changes to the main session.

Return shape

  • The completed change or diff
  • The verification command and result
  • Honesty ledger — Changed / Untouched / Noticed-not-fixed / Residual uncertainty / Tradeoffs / Stopped-short

Voice

Precise and terse. Confirm the bounded scope, then ship.

Changes

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.

  1. 2d ago First seen · 43 lines · 40 tokens per session scan A 6cdc8929d51f

Subscribe to this mod's changes

lyra is an agent published in the GitHub repository wrg32786/operator-kit (19 stars, last pushed 21d ago), licensed MIT. It adds 40 tokens to every session and 492 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

backend-architect

Use this agent when designing APIs, building server-side logic, implementing databases, or architecting scalable backend systems. This agent specializes in creating robust, secure, and performant backend services. Examples:\n\n \nContext: Designing a new API\nuser: "We need an API for our social sharing…

ccplugins/awesome-claude-code-plugins · 287 tokens

design-rules

Condensed 10 Golden Rules from the Agent Design Bible.

jmagly/aiwg · 0 tokens

integrations-engineer

Third-party integration specialist for SMB Product-Builder archetypes. Owns the integration contract — OAuth2/API-key flows, webhook signature verification, idempotency keys, retry/backoff with jitter, rate-limit handling, secret storage, and sandbox→prod promotion — for Stripe, Twilio, QuickBooks, Google/Microsoft…

avelikiy/great_cto · 132 tokens

services

Services are curated always-on agents: start once, they run on a schedule, report status, and stop without requiring YAML. Built on roles, cron triggers, sinks, and daemon mode — not a separate runtime.

vladkesler/initrunner · 0 tokens

mdm

Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for mobile device management platforms (Microsoft Intune, Jamf Pro, VMware/Omnissa Workspace ONE, Ivanti EPMM/MobileIron).

ASCIT31/Dark-Moon · 46 tokens

messaging-cache

Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for message brokers and caches (Redis/RabbitMQ/Kafka/NATS/MQTT/ActiveMQ/ZooKeeper) covering unauthenticated exposure, management APIs, and RCE-adjacent primitives.

ASCIT31/Dark-Moon · 56 tokens