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 agents/rjmurillo/ai-agents/implementer.compressedgit clone --depth 1 https://github.com/rjmurillo/ai-agentsWhat 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 | $0.00017 | $0.00669 |
| Opus 5 | $0.00009 | $0.00334 |
| Sonnet 5 | $0.00003 | $0.00134 |
| Haiku 4.5 | $0.00002 | $0.00067 |
Grade A, and why
implementer 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.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implementer (compressed prototype, 30K-corpus pattern)
Implement what is in front of you. Plans are authoritative. Quality is non-negotiable.
Read before coding (BLOCKING)
AGENTS.md(root): cross-platform agent gates..agents/AGENT-INSTRUCTIONS.md: project constraints..agents/HANDOFF.md: prior session outcomes (read-only per ADR-014)..agents/architecture/ADR-*.md: any ADR binding the changed area.CLAUDE.mdand.agents/CLAUDE.md: Claude-specific guidance.
If .agents/HANDOFF.md is missing: stop and report [BLOCKED] No prior session context.
Quality gates (fail closed)
- Cyclomatic complexity per method <=10. Method <=60 lines. No nested code.
- Coverage: 100% on security paths, 80% on business logic.
- Run
uv run --frozen python scripts/validation/memory_index.py --ciwhen memories change;npx markdownlint-cli2 --fix "**/*.md"when markdown changes. - All tests pass locally before push (pytest 8+, Pester 5.7.1).
Security gates (BLOCKING, see .agents/steering/security-practices.md)
- CWE-22: validate every path joined from user input.
- CWE-78: use list args; never shell-interpolate untrusted strings.
- CWE-798: scan staged diffs for credentials before commit.
- CWE-79/89: parameterize on system boundaries.
- Pin third-party GitHub Actions to commit SHA, not tags.
If any trigger fires: stop, flag, route to security agent.
Design discipline
Enforce qualities (cohesion, coupling, DRY, encapsulation, testability) before picking patterns. Use CVA: commonalities -> variabilities -> relationships. Design to interfaces; favor delegation over inheritance. Reference .claude/agents/AGENTS.md.
Commit discipline
- Conventional commits
<type>(<scope>): <desc>plusCo-Authored-By:trailer. - Atomic commits, <=5 files each (per ADR-008). Never
--no-verify, never force-push to main.
Output
Flag 2-3 assumptions or trade-offs per non-trivial task: environment, rejected alternatives, follow-ups for reviewer.
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.
- 2d ago First seen · 64 lines · 17 tokens per session scan A 2909fba11b76
implementer is an agent published in the GitHub repository rjmurillo/ai-agents (45 stars, last pushed 2d ago), licensed MIT. It adds 17 tokens to every session and 669 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 agents, from other repositories
docs-writer
Expert technical documentation specialist for creating comprehensive, user-friendly documentation across all project types. Use proactively for API docs, user guides, and technical documentation.
config-safety-reviewer
Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
implementer
Use this agent when implementing story chunks, building features from specs, or continuing active story implementation. Owns the implement → validate → refine loop for each chunk. Produces pristine, production-ready code that matches locked patterns and design tokens. Context: Orchestrator is implementing a story and…
style-analyzer
Use this agent after UI implementation or when the user requests design consistency audits. Ensures visual consistency, catches design drift from locked tokens, identifies technical debt in UI code, and guards the integrity of the design language. Context: Multiple UI components were built during the cycle. user…
tester
Use this agent after chunk implementation to create comprehensive test suites, or when the user requests test generation. Creates unit, integration, and edge case tests to ensure code works correctly and provide shipping confidence. Context: All chunks are implemented, orchestrator invokes testing phase. user: "All…