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/theam/claude-dev-kit/fix-prnpx skills add theam/claude-dev-kit --skill fix-prgit clone --depth 1 https://github.com/theam/claude-dev-kitWhat 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 | $0.00066 | $0.01275 |
| Opus 5 | $0.00033 | $0.00638 |
| Sonnet 5 | $0.00013 | $0.00255 |
| Haiku 4.5 | $0.00007 | $0.00128 |
Grade A, and why
fix-pr 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 2d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fix PR
Drive a PR's feedback to done: run a review, triage every item to a decision, fix what deserves fixing, file what deserves doing later, discard what deserves nothing, answer every reviewer, and re-check after pushing in case late feedback (bots, CI) arrives. The bar for correctness is high; the bar for new machinery is low — fix the defect, don't redesign around it.
1. Establish the PR intent (the scope ruler)
Write one or two sentences: what this PR is for, and what it deliberately does not change — derived from the title, body, linked issue, and the diff. Every scope call below is measured against it. If the intent is genuinely ambiguous, ask the author before triaging.
2. Gather the findings
Collect from every surface, deduplicated. Commands below are for github (prHost in .claude/dev-kit.json); for bitbucket use the REST API (/pullrequests/{id} comments, /statuses), for gitlab glab mr view/checks.
- CI failures:
gh pr checks <pr>— read the failing job logs, not just the status. - Review feedback: unresolved inline threads, review summary bodies, and PR conversation comments — bots included (
gh pr view <pr> --comments,gh apifor threads). Keep outdated threads: the code moved, the concern may not have. - Self-review findings handed over by the caller (the
pr-reviewpass).
3. Build the ledger
One row per distinct claim, merging duplicates across sources (if the review pass and a human flagged the same defect, that's one row citing both — and the human's thread still gets a reply):
| id | source | file:line | claim | category | verdict |
Assign exactly one verdict per row — nothing stays undecided:
FIX_NOW— fix it in this PR.DEFER_TO_ISSUE— real value, wrong moment → a tracked issue.DISCARD— not worth anyone's time; no fix, no issue.
Never DISCARD (from instructions/secure-coding.md + instructions/testing-standards.md): security/data-exposure, serious performance regressions, duplication this PR introduces, and missing test coverage for behavior it changes (when the project has tests). Only defer one of these when the fix is genuinely a separate project — and say so, treating the PR as blocked on the author's call, not quietly filing an issue.
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.
- 2d ago First seen · 59 lines · 66 tokens per session scan A 6c975cd3d6d5
fix-pr is a skill published in the GitHub repository theam/claude-dev-kit (11 stars, last pushed 2d ago), licensed Apache-2.0. It adds 66 tokens to every session and 1,275 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 2026-08-30.
Other skills, from other repositories
meridian-etl
Debug and work with Meridian's ETL pipeline. Covers session boundary detection, cursor management, DB queries, and common failure modes.
meridian-mcp
Build, configure, and debug the Meridian MCP server. Exposes app session data to AI tools via the Model Context Protocol.
session-summary
You summarise ONE work-burst of a developer's coding-agent session. The goal is to capture what the developer actually worked on, and why it mattered, so that a PM, a teammate, or the developer themselves can immediately understand the purpose and the outcome at a glance — without reading the transcript.
pir-action-tracker
Parses Post-Incident Review (PIR) pages in a Confluence space, fetches live status from referenced Jira tickets, updates action item tables with current status and due dates, marks completed PIRs with a visual closure panel, and surfaces any overdue actions for follow-up. Designed for Customer Success, Support, and…
jira-administration
Complete JIRA project and system administration including projects, automation rules, permissions, users, notifications, screens, issue types, and workflows. Use when managing project structure, automating work, configuring team access, or setting up issue tracking.
jira-service-management
Complete ITSM/ITIL workflow support for JSM - service desks, requests, SLAs, customers, approvals, knowledge base. Use when managing service desk requests, tracking SLAs, or handling customer operations.