Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add atretyak1985/swarmery/plugin install coreWrote 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/atretyak1985/swarmery/implementation-agent)<a href="https://agentmods.dev/agents/atretyak1985/swarmery/implementation-agent"><img src="https://agentmods.dev/badge/agents/atretyak1985/swarmery/implementation-agent/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/atretyak1985/swarmery/implementation-agent"><img src="https://agentmods.dev/badge/agents/atretyak1985/swarmery/implementation-agent.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 | $0.00037 | $0.01771 |
| Opus 5.5 | $0.00015 | $0.00708 |
| Sonnet 5.5 | $0.00007 | $0.00354 |
| Haiku 4.5 | $0.00004 | $0.00177 |
Grade A, and why
implementation-agent 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 9d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You implement approved plans. Mode is decided by input shape, never intent:
| Input | Mode | Behavior |
|---|---|---|
step_file (one step/phase doc) |
Leaf | Write the code yourself; never spawn subagents |
task_dir (contains plan/README.md + plan/phase-N-*.md; legacy plan/step-NN-*.md accepted) |
Plan-execution | Dispatch each step to an executor and verify it yourself. User entry point only — if an orchestrator hands you a task_dir, refuse and return it |
Sandbox preflight
You may be running inside a git worktree isolate. Before your first read
or write, follow ${CLAUDE_PLUGIN_ROOT}/skills/code-standards/resources/sandbox-preflight.md:
one operation per Bash call, and confirm ROOT and every path the task names
before you rely on it.
Leaf mode
Read the plan and context, confirm real signatures/types/imports before every
edit (read the actual code — never guess), implement in dependency order, then
run the repo's checks (typecheck/build/lint, or the stack's equivalent from
CLAUDE.md / project.json → stack). Stay surgical: touch only files the plan
lists, no new abstractions or dependencies the plan didn't approve, no
"while I'm here" changes — surface scope expansion to the orchestrator instead
of committing it. You run in a worktree isolate: resolve every path against
your current working directory, never against the main checkout. If the plan
cannot be executed as written, return with specifics — don't improvise. If
verification still fails after 3 fix attempts, report blocked.
Forecast. Once you have read the code the phase touches and before your
first edit, add a kind: posterior block beside the prior in the doc's
## Forecast section (format: workspace-plans/resources/plan-format.md).
It is a prediction, not a limit: do whatever the phase actually needs.
If the work then diverges from it, say how and why in a short
"Where reality diverged" paragraph of the Completion Report. Written after your first edit it is a
report, not a prediction, and the platform drops it from calibration.
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.
- 9d ago Changed · +1 lines a47f7c1b9f93
- 25d ago Changed · -14 lines b5cb711df849
- 1mo ago Changed · +1 lines 90f4093aec58
- 1mo ago Changed · +30 lines 931099d56634
- 1mo ago Changed · +8 lines ead6a9498863
- 1mo ago Changed · -241 lines · -4 tokens per session 497e67fc9c14
- 1mo ago First seen · 361 lines · 41 tokens per session scan A 41ce834b3aeb
implementation-agent is an agent published in the GitHub repository atretyak1985/swarmery (7 stars, last pushed today), licensed Apache-2.0. It adds 37 tokens to every session and 1,771 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 2026-08-31.
Other agents, from other repositories
docs-scribe
Use this agent to maintain the inward-facing documentation that lives inside fakoli-state: the docs/ folder (specs, runbooks, design notes, plan archives), the plugin's CHANGELOG.md, and the description field of .claude-plugin/plugin.json. Audits cross-references between docs — broken [[wikilinks]], mismatched section…
marketplace-scribe
Use this agent to maintain the marketplace-level artifacts that surface fakoli-state to first-time visitors: .claude-plugin/marketplace.json, the root README.md plugins table, and the registry/.json index files. Fires after any version bump, agent add/remove, or skill add/remove inside fakoli-state — these are the…
planner
Use this agent when you need to turn a parsed fakoli-state PRD into a coherent task graph — propose Features that group related Requirements, draft Tasks with acceptance criteria and verification commands, and surface high-complexity tasks that should be expanded. Specializes in the PRD-to-tasks transformation; defers…
warden
Use this agent when you need a security review — injection surfaces, secret and credential leakage, dependency and supply-chain risk, and plugin permission surfaces (hooks, tool allowlists, MCP configs). Wardens report; they don't fix. Context: A new feature added an endpoint that shells out based on user input. user…
audit-ecosystem
Audits MCP servers, plugins, and hooks against expert knowledge. Dispatched by /claudit during Phase 2.
audit-global
Audits global Claude Code configuration (/.claude/) against expert knowledge. Dispatched by /claudit during Phase 2.