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 skills add bestagentkits/agency-skills --skill decidegit clone --depth 1 https://github.com/bestagentkits/agency-skillsWrote 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/skills/bestagentkits/agency-skills/decide)<a href="https://agentmods.dev/skills/bestagentkits/agency-skills/decide"><img src="https://agentmods.dev/badge/skills/bestagentkits/agency-skills/decide/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/skills/bestagentkits/agency-skills/decide"><img src="https://agentmods.dev/badge/skills/bestagentkits/agency-skills/decide.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 | $0.00066 | $0.00892 |
| Opus 5 | $0.00033 | $0.00446 |
| Sonnet 5 | $0.00013 | $0.00178 |
| Haiku 4.5 | $0.00007 | $0.00089 |
Grade A, and why
decide 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/cs:decide — Log the Decision
Command: /cs:decide <memo-path>
Logs the founder's decision via the decision-logger skill. This is the gate where in-session deliberation becomes durable company memory.
Pipeline Position
/cs:office-hours → /cs:brief → /cs:boardroom → /cs:decide → /cs:execute → /cs:post-mortem
↑ you are here
Two-Layer Memory Model
The decision-logger skill maintains two layers:
- Raw transcripts — every boardroom session, every advisor's Phase 2 position, every dissent. Stored under
~/.claude/decisions/raw/. Reference only, never feeds back automatically. - Approved decisions — only the founder-signed memos. Stored under
~/.claude/decisions/approved/. Feeds into future/cs:office-hoursand/cs:founder-modecalls.
This split prevents the system from "remembering" unresolved debates as if they were decisions.
Input
A board memo file (output of /cs:boardroom).
Workflow
- Read the memo path
- Verify it has founder approval (status: APPROVED)
- Extract structured decision record:
- Decision title
- Date decided
- Option chosen
- Success + kill criteria
- Dissent (preserved)
- Review checkpoint date
- Append to
~/.claude/decisions/approved/<YYYY-MM-DD>-<slug>.md - Update the raw transcript pointer
- If llm-wiki bridge configured, write to vault (
~/company-vault/10-decisions/) - Schedule auto-revisit (90 days)
Output Record Format
# Decision: <title>
**Decided:** YYYY-MM-DD
**By:** <founder name>
**Memo:** <link to boardroom memo>
**Brief:** <link to original brief>
**Review checkpoint:** YYYY-MM-DD (90d default)
## Decision
**Chose:** <option>
**Rejected:** <other options + one-line why>
## Success Criteria (binding)
- <metric, threshold, timeframe>
## Kill Criteria (binding)
- <metric, threshold, action>
## Preserved Dissent
- **<dissenter>:** <unresolved concern>
- (preserved verbatim; dissent never erased)
## Next Action
- `/cs:execute` → 90-day plan due <date>
## Status History
- YYYY-MM-DD: APPROVED
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 First seen · 105 lines · 66 tokens per session scan A 00eee277c89e
decide is a skill published in the GitHub repository bestagentkits/agency-skills (11 stars, last pushed 2mo ago), licensed MIT. It adds 66 tokens to every session and 892 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
pod-resume
Reconstruct context for a returning developer. Reads .cocoplus/ state and generates a narrative summary of project status, last achievements, pending tasks, recent decisions, available patterns, CocoCupper insights, and recommended next action.
harness-step3-session-management
A project setup for keeping an agent’s work state in files between separate chat sessions. It creates a task list, a progress summary, and a script for checking the project environment.
bootstrap-agent-identity
Consistent agent behavior after restart — progressive identity loading, working context reconstruction from persistent artifacts, fresh-vs-continuation detection, calibration through centering and attunement, and identity verification for coherence. Addresses the cold-start problem where an agent must reconstruct who…
coordinate-reasoning
AI internal coordination using stigmergic signals — managing information freshness in context and memory, decay rates for assumption staleness, and emergent coherent behavior from simple local protocols. Use during complex tasks where multiple sub-tasks must coordinate, when context has grown long and information…
curate-collection
Build and maintain a library collection through acquisitions, weeding (deaccessioning), collection assessment, reader advisory, and interlibrary loan coordination. Covers selection criteria, collection development policies, the CREW/MUSTIE method for weeding, usage analysis, and responsive collection management. Use…
design-training-program
Design a GxP training programme covering training needs analysis by role, curriculum design (regulatory awareness, system-specific, data integrity), competency assessment criteria, training record retention, and retraining triggers for SOP revisions and incidents. Use when a new validated system requires user training…