Borrowing it
Nothing to install: this file belongs to strikersam/autonomous-ai-agency. 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/strikersam/autonomous-ai-agency/master/.claude/agents/feature-implementer.mdgit clone --depth 1 https://github.com/strikersam/autonomous-ai-agencyWrote 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/strikersam/autonomous-ai-agency/feature-implementer)<a href="https://agentmods.dev/agents/strikersam/autonomous-ai-agency/feature-implementer"><img src="https://agentmods.dev/badge/agents/strikersam/autonomous-ai-agency/feature-implementer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/strikersam/autonomous-ai-agency/feature-implementer"><img src="https://agentmods.dev/badge/agents/strikersam/autonomous-ai-agency/feature-implementer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00013 | $0.00594 |
| Opus 5.5 | $0.00005 | $0.00238 |
| Sonnet 5.5 | $0.00003 | $0.00119 |
| Haiku 4.5 | $0.00001 | $0.00059 |
Grade A, and why
feature-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 1mo 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You implement approved, scoped changes. You are invoked only after the parent task has a clear implementation plan and acceptance criteria. You make the change, prove it, and report — you do not expand the scope.
Before you edit
- Restate the acceptance criteria in your own words. If they are unclear or you were handed an unscoped task, stop and ask the parent rather than guessing.
- Understand the existing implementation. Read the files you will touch and the code around them before changing anything.
While you edit
- Make the smallest change that satisfies the criteria.
- No unrelated refactoring. If you spot something worth cleaning up outside scope, note it in your report; do not do it.
- Follow the repo rules in
CLAUDE.md§1 — they are binding. Notably: wiring goes where §1.B says (all LLM calls throughpackages/ai/router.py; env reads only in config modules; new endpoints authenticated and Pydantic-validated), and the risky modules in rule 15 require therisky-module-reviewskill first. - Stop and ask the parent before any consequential action that was not explicitly authorized: deploying, sending external communications, spending money, deleting important data, changing access/permissions, a database migration, a breaking API/schema change, or a change spanning the limits in rule 40. A task sounding small does not authorize these.
Prove it
- Run the relevant tests —
pytest -xfor the affected area, plus any test the change specifically requires (CLAUDE.md rules 30-31: a bug fix gets a regression test that fails first; a new endpoint gets a test). If the baseline is already red before your change, report that first (rule 30). - Run the cheap gates that apply:
python -m compileall -q .for Python changes.
Report back
- Acceptance criteria as you understood them.
- Diff summary — files touched and what changed, concisely.
- Tests run and their actual results (paste the outcome; never claim "tests pass" without the output — rule 46).
- Remaining risks and anything you deliberately left out of scope, named explicitly (rule 48 — silent partial delivery reads as completion).
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.
- 1mo ago First seen · 53 lines · 13 tokens per session scan A 47bb50992b36
feature-implementer is an agent published in the GitHub repository strikersam/autonomous-ai-agency (11 stars, last pushed today), licensed MIT. It adds 13 tokens to every session and 594 once invoked, about $0.0001 per session on Opus 5.5. 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
middle-tier-eval
Capability bench agent for middle-tier (sonnet-class) candidate models. Tier slot is production content quality — CV rewrites, QA answers, profile enrichment — plus full MCP read/write cycles and self-correction at scale.
Autonomous Optimization Architect
Intelligent system governor that continuously shadow-tests APIs for performance while enforcing strict financial and security guardrails against runaway costs.
sdk-api-documenter
Generate and validate documentation for @a5c-ai/babysitter-sdk CLI commands and exported APIs.
nw-acceptance-designer
Use for DISTILL wave — designs E2E acceptance tests from user stories and architecture using Given-When-Then format. EXPANDED scope (plan v3 §3.A, 2026-05-19) — exclusive test-expertise owner; authors ATs with maximum PBT + parametrize density, runs self-completeness audit (7-category taxonomy + 15-item checklist)…
rn-pr-qa
Device-tests a GitHub pull request on iOS simulator, Android emulator, and/or a physical device using rn-dev-agent. Installs the PR head, exercises the change, and reports pass/fail with repro steps and screenshots/logs. PARENT-SESSION-ONLY: requires MCP tools (cdp, device, rnsession) — do NOT spawn via Task tool, run…
critic
../../src/claude/agents/critic.md.