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.
npx agentmods add commands/sergei-aronsen/claude-code-toolkit/council-clear-cachegit clone --depth 1 https://github.com/sergei-aronsen/claude-code-toolkitWrote 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/commands/sergei-aronsen/claude-code-toolkit/council-clear-cache)<a href="https://agentmods.dev/commands/sergei-aronsen/claude-code-toolkit/council-clear-cache"><img src="https://agentmods.dev/badge/commands/sergei-aronsen/claude-code-toolkit/council-clear-cache.svg" alt="Measured on agentmods" 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 | $0.00016 | $0.00398 |
| Opus 5 | $0.00008 | $0.00199 |
| Sonnet 5 | $0.00003 | $0.00080 |
| Haiku 4.5 | $0.00002 | $0.00040 |
Grade A, and why
council-clear-cache 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 5d 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
/council clear-cache
Remove every cached /council result from ~/.claude/council/cache/.
Use it after editing your plan when the cache is masking your changes,
or when you want to force a fresh review.
Purpose
The Council caches identical requests by content hash so repeated
/council "<same plan>" calls inside the TTL (default 7 days) replay
the previous result without making API calls. This is great for cost
control but can be confusing if you tweaked the plan slightly and want
the reviewers to see the new version. clear-cache is the escape hatch.
When to Use
| Situation | Use /council clear-cache |
|---|---|
| Cached verdict feels stale after a rebase | yes — git HEAD changed but maybe not enough to invalidate |
| You want to A/B two prompt phrasings | yes — otherwise the second is a hit |
You want a full re-review without --no-cache |
yes |
| Disk usage on the cache dir matters | yes |
Usage
When the user types /council clear-cache (or asks to clear the
Council cache), invoke:
brain clear-cache
This empties ~/.claude/council/cache/*.json and prints the count of
removed entries. Show the output verbatim.
For a one-off bypass without clearing the cache, suggest the
--no-cache flag instead:
brain --no-cache "<plan>"
Notes
- The cache directory is left in place; only the JSON files are removed.
- Cache TTL is configurable via
config.cache.ttl_daysin~/.claude/council/config.json(default 7 days).
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.
- 5d ago First seen · 52 lines · 16 tokens per session scan A f644694b8926
council-clear-cache is a command published in the GitHub repository sergei-aronsen/claude-code-toolkit (5 stars, last pushed 19d ago), licensed MIT. It adds 16 tokens to every session and 398 once invoked, about $0.0001 per session on Opus 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.