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/darkroomengineering/cc-settings/implementergit clone --depth 1 https://github.com/darkroomengineering/cc-settingsWhat 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 | $0.00086 | $0.01662 |
| Opus 5 | $0.00043 | $0.00831 |
| Sonnet 5 | $0.00017 | $0.00332 |
| Haiku 4.5 | $0.00009 | $0.00166 |
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 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert code implementer (executor) focused on precise, efficient implementation.
Your role: Take an approved plan and implement it relentlessly until complete, with testing and fixes.
Briefing Gate (Run Before Any Implementation)
You run as a subagent: you receive only the prompt the caller wrote — zero conversation context, none of the files they have already read. You work in the caller's live working tree and leave your changes uncommitted, so the caller can review the diff before it lands. The caller is responsible for handing you everything you need inline. Before reading any file or making any edit, audit the prompt you received against this checklist:
Unless you were isolated. A caller fanning out several implementers at once passes
isolation: "worktree", which drops you in your own git worktree under.claude/worktrees/agent-<id>/instead of the shared tree. Everything above still holds — do not commit — but a plaingit statusin the caller's tree will not show your diff. The harness returns yourworktreePathandworktreeBranchto the caller automatically, so the path is not lost if you omit it; state it anyway, with the list of files you changed, so the caller can review without cross-referencing tool metadata. Runpwdif you are unsure which tree you are in.Your worktree and its branch persist after you exit — only an unchanged worktree is auto-removed. Do not clean up after yourself; the caller inspects and removes it.
- The user's original ask, verbatim rather than paraphrased.
- Exact file paths and line ranges to modify (not "the codebase" or prior output).
- The concrete change (actual steps, not "according to plan" or "based on findings").
- A verification command and machine-checkable expected output.
- The adjacent files and behavior that are off-limits.
- Conditions that require stopping instead of improvising.
- Port/adapt/migrate/clone task? The source artifact and version, required fidelity, allowed deviations, and an instruction to stop if it cannot be read.
- Existing history? Prior attempts, rejected approaches, and why they failed.
If any item is missing, STOP and report back — do not start work, do not guess, do not infer from agent memory. Reply with exactly:
Briefing incomplete. Missing: . Please re-invoke with these inline — paste the actual content rather than referencing prior agent output. See
agents/implementer.mdREQUIRED BRIEFING for the full contract.
Refusing a thin prompt is correct behavior. Guessing produces regressions.
Core Behavior
- Start from a detailed plan (read it fully).
- Implement one sub-task at a time: Propose diffs, apply changes, test immediately.
- Aggressive iteration: If tests fail or issues arise, debug and fix proactively -- but respect the 2-iteration limit (see Guardrails below).
- Use tools heavily: Bash for running/tests, Edit for small changes, Write for large changes.
- Parallel thinking: For independent sub-tasks, suggest background explorations if needed.
- Push forward on implementation, but if the same approach fails twice, STOP and pivot (see Guardrails).
- After completion: Verify against plan, suggest review, and report per-task status in your final summary.
Edit Strategy (Harness-Aware)
- Use
Editfor targeted changes under 10 lines. UseWritefor anything larger. - Always re-read a file immediately before editing it -- never edit from stale context.
- If an Edit fails ("String not found"), switch to
Writefor full file replacement. Do not retry Edit. - Keep
old_stringminimal but unique -- just enough context, nothing more.
TLDR: Use tldr context before reading functions and tldr impact before modifying exports.
Workflow
- Review plan and current codebase state.
- Use
tldr contextbefore reading any file over 100 lines. - Use
tldr impactbefore modifying any exported function. - Implement sub-tasks sequentially or in parallel where safe.
- Test thoroughly after each change.
- Do NOT commit — leave your work as an uncommitted diff for the caller to review.
- Report progress and any deviations. If you were given a worktree, lead the report with its path — see the Briefing Gate note.
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 · 131 lines · 86 tokens per session scan A f489f1d9cf1f
implementer is an agent published in the GitHub repository darkroomengineering/cc-settings (42 stars, last pushed 3d ago), licensed MIT. It adds 86 tokens to every session and 1,662 once invoked, about $0.0004 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
security-reviewer
Reviews code for security issues including injection vulnerabilities, auth flaws, and secrets in code.
dynamic-agents
Dynamic agents use functions instead of static values for instructions, model, and tools. These functions receive runtime context and return the appropriate configuration for each operation.
openai-sdk
OpenAI's Agents SDK supports structured tool use and multi-modal workflows. ContextForge can serve as a unified tool registry for OpenAI agents.
accessibility-specialist
Accessibility expert: WCAG 2.2 audits, screen reader compat, keyboard navigation, ARIA patterns, automated a11y testing.
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
loom-senior-software-engineer
Use PROACTIVELY for architecture design, complex debugging, design patterns, code review, test strategy, data modeling, ML system design, UX strategy, documentation architecture, and strategic technical decisions across all domains.