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 skills/perseus-computing-llc/perseus/pir-action-trackernpx skills add Perseus-Computing-LLC/perseus --skill pir-action-trackergit clone --depth 1 https://github.com/Perseus-Computing-LLC/perseusWrote 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/perseus-computing-llc/perseus/pir-action-tracker)<a href="https://agentmods.dev/skills/perseus-computing-llc/perseus/pir-action-tracker"><img src="https://agentmods.dev/badge/skills/perseus-computing-llc/perseus/pir-action-tracker.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 | $0.00078 | $0.02812 |
| Opus 5 | $0.00039 | $0.01406 |
| Sonnet 5 | $0.00016 | $0.00562 |
| Haiku 4.5 | $0.00008 | $0.00281 |
Grade A, and why
pir-action-tracker 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 — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PIR Action Tracker Skill
Automates the maintenance of Post-Incident Review (PIR) pages in Confluence by syncing action item status from Jira, flagging overdue items, and marking completed PIRs with a visible closure panel.
What This Skill Does
- Discovers candidate PIR pages in a configured Confluence space, then keeps only pages with qualifying internal-action tables
- Parses every qualifying action item table — extracts ticket references, current status, and target/due/completion dates where present
- Fetches live status for each referenced Jira ticket
- Updates each retained PIR page in-place with the latest status and target/due/completion dates where present
- Closes completed PIRs with a prominent green ✅ success panel listing what was accomplished
- Reports any overdue or unverifiable actions for human follow-up
Configuration
Before running, set these variables in your prompt or environment:
| Variable | Example | Description |
|---|---|---|
CONFLUENCE_SITE |
your-org.atlassian.net |
Confluence site hostname |
CONFLUENCE_SPACE |
MYSPACE |
Space key to scan for PIR pages |
PIR_SEARCH_TERM |
PIR |
Title keyword used to find PIR pages (default: "PIR") |
JIRA_SITE |
your-org.atlassian.net |
Primary Jira site for ticket lookups |
TICKET_PREFIX_MAP |
See below | Map ticket prefixes to Jira sites |
Ticket Prefix Map (optional)
If your PIRs reference tickets across multiple Jira sites, provide a prefix-to-site map:
CMON, SAM → hello.atlassian.net
PIRA → opsj.atlassian.net
MEP → experimentation-platform.atlassian.net
Tickets on inaccessible external sites are flagged in the report but not updated.
Trigger Phrases
- "update the PIR tracker"
- "check PIR action items"
- "sync PIR pages"
- "any overdue PIR actions?"
- "close completed PIRs"
- "PIR status update"
Workflow
Step 1 — Discover Candidate PIR Pages
search_confluence_using_cql(
site_url="{CONFLUENCE_SITE}",
cql='space = "{CONFLUENCE_SPACE}" AND title ~ "{PIR_SEARCH_TERM}" AND type = page ORDER BY lastModified DESC',
limit=50
)
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 · 306 lines · 78 tokens per session scan A 76a6d8944425
pir-action-tracker is a skill published in the GitHub repository Perseus-Computing-LLC/perseus (43 stars, last pushed yesterday), licensed MIT. It adds 78 tokens to every session and 2,812 once invoked, about $0.0004 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 skills, from other repositories
write-workflow-as-code
MUST use when writing or modifying Windmill Workflow-as-Code scripts using workflow, task, step, sleep, approvals, taskScript, taskFlow, taskscript, or taskflow.
cmux
End-user control of cmux topology and routing (windows, workspaces, panes/surfaces, focus, moves, reorder, identify, trigger flash). Use when automation needs deterministic placement and navigation in a multi-pane cmux layout.
release
Automate project release workflow with version management, CHANGELOG updates, and git operations.
daf-jira-mcp
Using MCP JIRA tools with DevAIFlow validation logic and field intelligence.
daf-jira-fields
JIRA field mapping rules, validation, and defaults for DevAIFlow.
daf-jira
JIRA operations (view, create, update, comment) with Wiki markup syntax reference.