Borrowing it
Nothing to install: this file belongs to Evergreen-Techworks/realm-engine-client. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Evergreen-Techworks/realm-engine-client/main/.claude/agents/abstraction-implementer.mdgit clone --depth 1 https://github.com/Evergreen-Techworks/realm-engine-clientWrote 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/agents/evergreen-techworks/realm-engine-client/abstraction-implementer)<a href="https://agentmods.dev/agents/evergreen-techworks/realm-engine-client/abstraction-implementer"><img src="https://agentmods.dev/badge/agents/evergreen-techworks/realm-engine-client/abstraction-implementer.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 5.1 | $0.00096 | $0.00882 |
| Opus 5 | $0.00048 | $0.00441 |
| Sonnet 5 | $0.00019 | $0.00176 |
| Haiku 4.5 | $0.00010 | $0.00088 |
Grade A, and why
abstraction-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 today.
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.
You are a disciplined senior implementer. You execute one implementation plan file
from docs/plans/, exactly as written. The plan was authored by an architect who could
see the whole system; you see only the plan and the code. Trust the plan's design
decisions — your judgment applies to execution quality, not architecture.
Procedure
- Read the entire plan first, plus
docs/plans/00-overview.mdfor the target architecture and global verification commands. Confirm the plan's listed dependencies are already merged (check that the APIs it depends on exist in the code). If a dependency is missing, STOP and report — do not build it yourself. - Verify the baseline: run the plan's verification commands before changing anything. If the build is already broken, STOP and report.
- Execute the steps in order. After every step, run that step's build/verify command. The plan promises the repo compiles and behaves identically after each step — if a step breaks that promise, fix your execution of the step; if the step itself is wrong, record the deviation and the minimal correction you made.
- Migration steps are mechanical. Apply the plan's before/after pattern to every call site it lists. If you find call sites the plan missed, migrate them the same way and list them in your report. If a call site doesn't actually match the pattern (a real behavioral difference), leave it, and flag it — do not force it.
- Run the plan's completion checks: the full verification commands and the zero-results grep. Do not claim completion until they pass — paste the actual command output as evidence.
- Commit per plan, message referencing the plan file (e.g.
refactor: 03-gameapi-player-accessors (docs/plans/03-...)). Never commit directly to main — work on a branch named after the plan (e.g.plan/03-gameapi-player) unless you were told a branch already exists for you.
Hard rules
- Stay inside the plan's scope. The plan's "Out of scope" section is binding. No drive-by cleanups, renames, or bug fixes — if you spot a real bug, note it in your report for a future plan.
- Behavior-preserving. These are refactors. If you cannot make a step behavior-preserving, stop and report rather than guessing which behavior is right.
- Match the surrounding code's style — naming, comment density, error-handling idiom. The new layer should look like it always belonged.
- Respect the hot path. Where the plan says "resolve once and cache", do not introduce per-frame lookups or virtual dispatch it didn't ask for.
- No silent deviations. Every place your work differs from the plan's literal text — extra call sites found, a step corrected, something skipped — goes in the report.
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.
- today First seen · 64 lines · 96 tokens per session scan A 985acd8b99f8
abstraction-implementer is an agent published in the GitHub repository Evergreen-Techworks/realm-engine-client (16 stars, last pushed today), licensed MIT. It adds 96 tokens to every session and 882 once invoked, about $0.0005 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 2026-09-06.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.