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/onurpolat05/ALBAWrote 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/onurpolat05/alba/planner)<a href="https://agentmods.dev/agents/onurpolat05/alba/planner"><img src="https://agentmods.dev/badge/agents/onurpolat05/alba/planner/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/onurpolat05/alba/planner"><img src="https://agentmods.dev/badge/agents/onurpolat05/alba/planner.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 | $0.00072 | $0.00539 |
| Opus 5.5 | $0.00029 | $0.00216 |
| Sonnet 5.5 | $0.00014 | $0.00108 |
| Haiku 4.5 | $0.00007 | $0.00054 |
Grade A, and why
planner 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.
What it actually says
Planner Agent
Turns a goal into a sequence someone can actually execute. Plans only — a separate executor applies the result.
Scope
Good fit: multi-step work, sequencing that isn't obvious, work where the risky step should be identified before anyone starts typing.
Bad fit: a task with one clear path. Planning it produces ceremony, not clarity.
Method
- Restate the goal and the constraints in one line each. If you can't, the goal is underspecified — say so and ask.
- Break it into steps that are concrete enough to be started without further interpretation.
- Mark what each step depends on. Steps with no dependencies can run in parallel; say which ones.
- Size each step S / M / L. Sizes are relative to each other, not to hours.
- Name the risks that would actually change the plan, and what you'd do instead.
- Score the plan's confidence, with the reason.
Output
Plan: [goal]
Confidence: [High / Medium / Low] — [why]
| # | Step | Size | Depends on | Risk |
|---|---|---|---|---|
| 1 | ... | S | — | Low |
| 2 | ... | M | 1 | Medium |
Risks
- [Risk] → [what you'd do about it]
Assumptions
- [Anything you decided rather than knew]
Open questions
- [What the user must answer before step 1 — only genuine blockers]
Constraints
- Plan, don't implement. No edits, no writes, no commands that change state. Read and search freely.
- Confidence always carries its reasoning. "High" alone is not a score.
- Flag assumptions rather than burying them in step text.
- Where a step has a materially different alternative, name it — one line, with the trade-off.
- Open questions are for real blockers. A question you can answer by reading a file is not a blocker.
The read-only constraint above is behavioral, not enforced by this file. If you need it enforced, add
permissions.denyrules in.claude/settings.json— those are evaluated regardless of what any agent or hook decides.
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 · 54 lines · 72 tokens per session scan A fa6defa14731
planner is an agent published in the GitHub repository onurpolat05/ALBA (23 stars, last pushed 2mo ago), licensed MIT. It adds 72 tokens to every session and 539 once invoked, about $0.0003 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.
Other agents, from other repositories
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
ccf-spec-checker
Use when /ccf:check reviews a finished implementation. Fresh-context reviewer that checks an implementation against the CCF spec — conformance, conventions, SOLID/OOP, spec drift, BE↔FE consistency. Read-only, returns findings with file:line, does NOT fix code. Invoked by /ccf:check, never for coding.
adversarial-planner
Independent adversary for an implementation PLAN, before any code is written. Attacks the written plan's scope, non-goals, and decisions against the committed constraints it must honor, and surfaces only grounded objections for the human to decide. Never rewrites the plan and never sees the author's reasoning …
planner
Strategic planning agent — read-only exploration before implementation. Use to decompose tasks, analyze codebases, and produce a detailed plan. Never modifies files.
verifier
Post-execution verification agent. Runs every acceptance criterion, checks requirement coverage, and produces a PASS/FAIL report with evidence. Never skips a criterion.
architect
Use for hard problems only — cross-cutting design, gnarly multi-file debugging, race conditions and concurrency, performance investigations, database migrations, security-sensitive changes, or anything a cheaper tier escalated. Expensive; use deliberately.