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/gonzalezpazmonica/saviaWrote 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/gonzalezpazmonica/savia/backlog-sync)<a href="https://agentmods.dev/commands/gonzalezpazmonica/savia/backlog-sync"><img src="https://agentmods.dev/badge/commands/gonzalezpazmonica/savia/backlog-sync/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/commands/gonzalezpazmonica/savia/backlog-sync"><img src="https://agentmods.dev/badge/commands/gonzalezpazmonica/savia/backlog-sync.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 | $0.00022 | $0.00371 |
| Opus 5.5 | $0.00009 | $0.00148 |
| Sonnet 5.5 | $0.00004 | $0.00074 |
| Haiku 4.5 | $0.00002 | $0.00037 |
Grade A, and why
backlog-sync 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.
This is a copy
100% identical to backlog-sync — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
/backlog-sync
Synchronize local markdown backlog with external PM tools.
Providers
| Provider | Adapter | Requirements |
|---|---|---|
| azure-devops | sync-adapters/azure-devops-adapter.sh | AZURE_DEVOPS_ORG_URL + PAT |
| jira | sync-adapters/jira-adapter.sh | JIRA_BASE_URL + email + token |
| github | sync-adapters/github-issues-adapter.sh | gh CLI + --repo |
Actions
- pull: Download items from external tool, merge into local backlog
- push: Upload local PBIs to external tool (creates new, updates existing)
- diff: Show differences without applying changes
Conflict Policy
- Both changed: show diff, ask PM to decide
- Only local changed: push
- Only remote changed: pull
- NEVER auto-resolve state, estimation, or assignment conflicts
Steps
- Detect provider from project _config.yaml or --provider flag
- Validate credentials and connectivity
- Execute requested action via adapter script
- Log sync operation to output/.sync-log.jsonl
- Show summary with counts
Output
Sync: local ↔ azure-devops (project-name)
Created: 2 | Updated: 3 | Conflicts: 0 | Skipped: 1
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 Changed 8b1d6455d780
- 1mo ago First seen · 50 lines · 22 tokens per session scan A 83113c787be8
backlog-sync is a command published in the GitHub repository gonzalezpazmonica/savia (50 stars, last pushed today), licensed MIT. It adds 22 tokens to every session and 371 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to backlog-sync, differing in 2 lines, and is treated as a copy.
Other commands, from other repositories
wtfp:contribute
Guide a bounded WTF-P contribution from branch creation through a reviewable change request.
pr-summary
Summarize accessible open GitHub pull requests from structured gh JSON, filtering bots and grouping results by ticket. Use for a read-only PR status report. Not for: changing PR state, reviewing code, merging, or closing PRs. Output: grouped Markdown written to /tmp/pr-summary.md and displayed for copying.
contribute
Guide a bounded WTF-P contribution from branch creation through a reviewable change request.
project
Manage projects: register repos, inspect, configure per-project settings, and remove.
land
Resolve and squash merge one named, currently authorized pull request.
repo-architect
Repository structure optimization and multi-repo management with ruv-swarm coordination for scalable project architecture and development workflows.