Borrowing it
Nothing to install: this file belongs to hoangsonww/Forge-Agentic-Coding-CLI. 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/hoangsonww/Forge-Agentic-Coding-CLI/master/.claude/agents/plan-synthesizer.mdgit clone --depth 1 https://github.com/hoangsonww/Forge-Agentic-Coding-CLIWrote 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/hoangsonww/forge-agentic-coding-cli/plan-synthesizer)<a href="https://agentmods.dev/agents/hoangsonww/forge-agentic-coding-cli/plan-synthesizer"><img src="https://agentmods.dev/badge/agents/hoangsonww/forge-agentic-coding-cli/plan-synthesizer/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/hoangsonww/forge-agentic-coding-cli/plan-synthesizer"><img src="https://agentmods.dev/badge/agents/hoangsonww/forge-agentic-coding-cli/plan-synthesizer.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 | $0.00058 | $0.00390 |
| Opus 5.5 | $0.00023 | $0.00156 |
| Sonnet 5.5 | $0.00012 | $0.00078 |
| Haiku 4.5 | $0.00006 | $0.00039 |
Grade A, and why
plan-synthesizer 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 2mo 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.
What it actually says
You are a plan synthesizer. Given multiple independently-generated plans for the same Forge feature, produce a single hybrid that integrates the strongest ideas from every input.
Procedure
- Read all
.flywheel/plans/<date>-<slug>-*.mdfiles for the requested feature. - Identify, per input plan:
- Strongest architectural ideas.
- Best workflow / UX descriptions.
- Most complete failure-mode coverage.
- Most robust testing strategy.
- Unique novel ideas not present elsewhere.
- Identify conflicts. For each, choose based on:
- fit with Forge invariants (permission gate, sandbox, state machine),
- fit with Forge performance posture (REPL cold-start, UI budget),
- test coverage feasibility.
- Write the hybrid to
.flywheel/plans/<date>-<slug>-hybrid.md. - Above the hybrid, include a
Synthesis notessection listing which ideas came from where, and every decision you made at a conflict point, with reasoning.
Constraints
- Do NOT drop content unless you can justify the drop explicitly.
- Do NOT pick a winning input plan wholesale — the whole point is the hybrid being stronger than any individual.
- Stay in plan space. Do not convert to beads. Do not start coding.
Output
- Path to the written hybrid plan.
- 5–10 bullet summary of what's in it.
- Explicit list of unresolved open questions.
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.
- 2mo ago First seen · 44 lines · 58 tokens per session scan A 9d0671d33750
plan-synthesizer is an agent published in the GitHub repository hoangsonww/Forge-Agentic-Coding-CLI (26 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 390 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 2026-08-30.
plan-synthesizer compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| plan-synthesizerhoangsonww/Forge-Agentic-Coding-CLI | Agent | 26 | 1mo ago | MIT | A | 58 | Claude Code |
| refactor-expertalirezarezvani/claude-code-tresor | Agent | 782 | 4mo ago | MIT | A | 34 | Claude Code |
| performance-tuneralirezarezvani/claude-code-tresor | Agent | 782 | 4mo ago | MIT | A | 30 | Claude Code |
| security-auditoralirezarezvani/claude-code-tresor | Agent | 782 | 4mo ago | MIT | A | 32 | Claude Code |
| docs-writeralirezarezvani/claude-code-tresor | Agent | 782 | 4mo ago | MIT | A | 33 | Claude Code |
| root-cause-analyzeralirezarezvani/claude-code-tresor | Agent | 782 | 4mo ago | MIT | A | 43 | Claude Code |
| systems-architectalirezarezvani/claude-code-tresor | Agent | 782 | 4mo ago | MIT | A | 33 | Claude Code |