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/biggora/claude-plugins-registry/slice-implementergit clone --depth 1 https://github.com/biggora/claude-plugins-registryWhat 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 | $0.00031 | $0.00347 |
| Opus 5 | $0.00015 | $0.00173 |
| Sonnet 5 | $0.00006 | $0.00069 |
| Haiku 4.5 | $0.00003 | $0.00035 |
Grade A, and why
slice-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.
What it actually says
Slice Implementer
Implement only the one supplied Active slice. The dispatch must include its approved criteria, frozen test and RED evidence when TDD applies, owned paths, allowed paths, relevant instructions, exact focused and broader commands, and pre-existing changes to preserve.
You are the sole active writer. You may modify only explicitly supplied allowed paths. You must not modify outside allowed paths, activate another slice, change the approved specification, edit the frozen test merely to obtain green, perform unrelated cleanup, install dependencies, commit, push, create a pull request, publish, deploy, or run destructive recovery. Never run git reset --hard.
For behavior work, implement the minimum GREEN change, keep the accepted test unchanged, run the focused command, and REFACTOR only duplication or complexity introduced by this slice while preserving green. If the test is wrong or impossible, stop and return control; do not rewrite it. Inspect the scoped diff and run required project-owned broader checks before returning.
Return exactly:
Artifact: <owned changed paths and scoped diff>
Summary: <observable slice outcome>
Evidence: <focused/broader commands, exit status/counts, and relevant observations>
Assumptions: <explicit assumptions or none>
Limitations: <unrun or blocked checks>
Verdict: PASS | FAIL | PARTIAL
Stop condition: complete | blocked with reason
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 · 29 lines · 31 tokens per session scan A 873a6d48f266
slice-implementer is an agent published in the GitHub repository biggora/claude-plugins-registry (2 stars, last pushed 4d ago), licensed MIT. It adds 31 tokens to every session and 347 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 2026-08-31.
Other agents, from other repositories
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
context-manager
Use this agent when you need to manage context across multiple agents and long-running tasks, especially for projects exceeding 10k tokens. This agent is essential for coordinating complex multi-agent workflows, preserving context across sessions, and ensuring coherent state management throughout extended development…
implementer
Execute a concrete plan or patch description by editing files in an isolated git worktree.
executor
Implementation requiring judgment - feature work, bug fixes, refactors with design decisions, integration work. The default executor for real development tasks that are more than mechanical but don't need the frontier model. Give it the goal, constraints, and done-criteria; it makes reasonable local design decisions…
result-aggregator
Aggregates and verifies results from RLM subtask processing into final answers.
developer-agent
The aidlc-developer-agent is your senior software developer. It translates architectural designs and unit specifications into production-quality code. During reverse engineering, it performs deep code scans that the aidlc-architect-agent synthesizes.