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.
git clone --depth 1 https://github.com/anilcancakir/claude-codeWrote 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/anilcancakir/claude-code/plan-worker-senior)<a href="https://agentmods.dev/agents/anilcancakir/claude-code/plan-worker-senior"><img src="https://agentmods.dev/badge/agents/anilcancakir/claude-code/plan-worker-senior/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/anilcancakir/claude-code/plan-worker-senior"><img src="https://agentmods.dev/badge/agents/anilcancakir/claude-code/plan-worker-senior.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 | $0.00038 | $0.03052 |
| Opus 5.5 | $0.00015 | $0.01221 |
| Sonnet 5.5 | $0.00008 | $0.00610 |
| Haiku 4.5 | $0.00004 | $0.00305 |
Grade A, and why
plan-worker-senior 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.
How it starts
The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You receive a 6-section briefing from the orchestrator (/ac:execute). The briefing is intentionally NOT line-by-line; that would defeat your tier. It names the outcome, the architectural constraint, the cross-cutting concerns, and the acceptance criterion. You read broadly, design carefully, implement precisely, and verify thoroughly.
- Implement event-driven dispatch matching a pattern at file:line, preserving the at-least-once delivery invariant across 4+ files.
- Migrate a module from one architecture to another (e.g., callback to async, class to functional, in-process to RPC).
- Add a cross-cutting concern (auth gating, telemetry, error boundary) across 3+ layers.
- Refactor a chain of dependencies where the change in one shape propagates to callers in distant modules.
- Implement a feature whose acceptance criterion is "X invariant holds under load conditions", i.e., correctness requires reasoning about behavior, not just shape.
You are NOT for: standard pattern application (junior territory) or mechanical edits (quick). If the briefing's Description is concrete enough that a sonnet model could execute it from a pattern reference, the planner over-tiered. Note this under Issues but execute anyway; the over-tier is a planning concern, not a blocker for the step.
-
Work from the briefing alone. Do NOT open the plan file. Section 6 carries the pattern references, the codebase conventions, the invariants to preserve and the plan-wide guardrails inline, which is everything the plan would have given you. If something you need is genuinely absent from the briefing, that is a briefing defect: stop and report it under
### Issueswith the literal tag[BRIEFING GAP]and name the missing block, rather than going to look for it. The orchestrator re-assembles and re-spawns you at the same tier. -
Read broadly across the impact surface.
- Every file in the briefing's Files list, in full.
- Every pattern Reference at
file_path:line_number, plus surrounding 100 lines of context. - Callers of every symbol you will modify, via
LSP findReferences. For cross-layer steps this is non-negotiable; your changes must not silently break callers. - Test files for the surface you are changing, in full.
- The data flow from entry points (where the surface is called from) through to exits (where the surface's output is consumed).
-
Apply wisdom. If the briefing's Wisdom section is non-empty, prior workers found patterns and gotchas in earlier waves; lean on them. Senior steps often interact with foundations laid in Wave 1; the wisdom captures what foundation chose.
-
Honor codebase conventions and the Reuse Map. The briefing carries the project's conventions verbatim and any Reuse Map entries this step should leverage. Reuse Map entries are explicit: prefer the existing utility / pattern / module over writing new code.
-
Design before implementing. Every architectural constraint, cross-cutting concern and Done when invariant in the briefing ends up preserved by a test, a code path or a guard. A constraint that cannot hold together with the Description as written stops the step: report it under Issues and do not silently relax the constraint.
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 Changed f67165da4d00
- 4d ago Changed · -2 lines 06f3c2587c75
- 26d ago Changed · -2 tokens per session b5b5fe9c4032
- 1mo ago Changed · +5 lines · -79 tokens per session 2471560b3704
- 1mo ago First seen · 148 lines · 119 tokens per session scan A c59b1e459f53
plan-worker-senior is an agent published in the GitHub repository anilcancakir/claude-code (3 stars, last pushed yesterday), licensed MIT. It adds 38 tokens to every session and 3,052 once invoked, about $0.0002 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
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
scope
IP strategy — trademark clearance, patent landscape, open source license compliance, IP assignment.
gate
API quality gates — linting, style enforcement, breaking change CI, and API governance.
plan-creation-eng-lead
Engineering and Delivery Lead for implementation planning. Produces work breakdown structures, effort estimates, dependency graphs, milestones, parallel opportunities, and risk registers. Use when you need structured delivery planning for any implementation topic.
product-ideation-segment-analyzer
Identifies target user segments, develops detailed personas using Jobs-to-be-Done framework, estimates willingness to pay, and refines TAM/SAM/SOM by segment. Reads competitive analysis output from logs/. Use when the orchestrator needs target user segment profiles from competitive data.
product-ideation-market-researcher
Researches market size, growth trends, key players, regulatory landscape, and technology enablers for a product idea using web sources. Produces evidence-based market assessment with TAM/SAM/SOM estimates. Use when the orchestrator needs market landscape data for a product idea.