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/iliaal/whetstone/prune-sync-loggit clone --depth 1 https://github.com/iliaal/whetstoneWrote 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/iliaal/whetstone/prune-sync-log)<a href="https://agentmods.dev/commands/iliaal/whetstone/prune-sync-log"><img src="https://agentmods.dev/badge/commands/iliaal/whetstone/prune-sync-log.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 | $0.00017 | $0.01200 |
| Opus 5 | $0.00009 | $0.00600 |
| Sonnet 5 | $0.00003 | $0.00240 |
| Haiku 4.5 | $0.00002 | $0.00120 |
Grade A, and why
prune-sync-log 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.
How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prune sync log
Archive entries in docs/audit/audit-log.md that are no longer load-bearing, so the pre-flight filter in /sync-from-repos and /audit-plugin stays lean and current.
Configuration
SYNC_LOG=docs/audit/audit-log.md
ARCHIVE=docs/audit/audit-log-archive.md
PLUGIN_DIR=plugins/whetstone
REPOS_DIR=~/ai/repos
TODAY=YYYY-MM-DD # resolve to actual date at run time
Phase 1: Inventory
Read $SYNC_LOG in full. Parse it into run entries keyed by (date, type, scope). For each entry, extract every bullet under Applied / Rejected / Deferred along with the component it targets.
If the file doesn't exist, report that and stop.
Phase 2: Classify each entry
For every run entry, assign one of four statuses. Classification happens at the entry level (whole run), not per bullet, because entries are the unit of append.
| Status | Criteria | Action |
|---|---|---|
| Keep | Entry <30 days old AND every referenced component still exists AND reasoning not superseded AND referenced repos still in $REPOS_DIR |
Leave in place |
| Prune — age | Entry >30 days old and no longer load-bearing for current plugin state | Move to archive |
| Prune — stale-ref | One or more bullets reference a component path that no longer exists under $PLUGIN_DIR, OR an external repo no longer in $REPOS_DIR |
Move to archive (even if <30 days — stale refs confuse the filter) |
| Prune — superseded | Reasoning for a rejection has been promoted to a feedback-memory rule in MEMORY.md, or a later entry applies the same change and overrides the rejection |
Move to archive |
Stale-ref detection: for each bullet, resolve the backtick-quoted component name to a path under $PLUGIN_DIR (skills/agents/commands). Use Glob or Grep to confirm existence. If the entry references an external repo by name (e.g., "Source repo: gstack"), check for $REPOS_DIR/gstack/.
Supersession detection: read ~/.claude/projects/-home-ilia-ai-whetstone/memory/MEMORY.md and scan feedback entries. If a rejection reason in a log bullet matches the rule in a feedback entry (same pattern, same target), mark the bullet as superseded. When more than half of an entry's bullets are superseded, prune the entry.
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 · 98 lines · 17 tokens per session scan A 276715a7d532
prune-sync-log is a command published in the GitHub repository iliaal/whetstone (32 stars, last pushed 6d ago), licensed MIT. It adds 17 tokens to every session and 1,200 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 2026-08-30.
Other commands, from other repositories
composite-actions
Generate, review, secure, and test composite GitHub Actions following best practices — full repo scaffold, interview-driven generation, PR creation on existing repos, SHA pinning, secrets-as-inputs, job summaries, and actionlint validation.
github-actions
Design, review, secure, and debug GitHub Actions workflows — reusable workflows, OIDC federation, SHA pinning, token scoping, promotion orchestration, and CI failure diagnosis.
datadog
Set up and troubleshoot Datadog — Agent deployment on Kubernetes, APM instrumentation, Log Management, Monitors, Dashboards, SLOs, Synthetic tests, and live incident investigation using the Datadog MCP server. Covers Terraform-managed Datadog resources.
fluxcd
FluxCD entry point — routes to the right workflow based on what you need. Live cluster issue → structured 5-workflow debug trace. Repo health check → 6-phase audit (discovery, validation, API compliance, best practices, security). Helm chart review → helmchart. Starts by asking one question to confirm the right mode.
linkerd
Linkerd-specific diagnostics — mTLS verification, proxy injection issues, authorization policy debugging, traffic management, and multi-cluster connectivity problems.
terraform
Runs through the full Terraform validation pipeline — fmt, validate, tflint, security scan — and reviews a module or plan for blast radius, IAM risk, and state impact.