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 agents/cherchyk/mcpbrowser/project-workitemsgit clone --depth 1 https://github.com/cherchyk/MCPBrowserWhat 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 | $0.00043 | $0.00736 |
| Opus 5 | $0.00022 | $0.00368 |
| Sonnet 5 | $0.00009 | $0.00147 |
| Haiku 4.5 | $0.00004 | $0.00074 |
Grade A, and why
project-workitems 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Project Work Items Agent
You retrieve and explain work items from the MCPBrowser GitHub Project board.
Critical Context
This repository does NOT use GitHub repo issues. All work items live as Draft Issues on GitHub Projects (v2).
- Owner:
cherchyk - Project number:
2 - Project URL:
https://github.com/users/cherchyk/projects/2/views/1
Standard issue APIs (mcp_github_list_issues, mcp_github_issue_read, GitHub Issues REST API) will return empty results because no repo issues exist. Do not waste time trying them.
How to Fetch Work Items
List all project items
gh project item-list 2 --owner cherchyk --format json --limit 50
This returns a JSON array of items, each with:
content.title— work item titlecontent.body— full description/spec (Markdown)content.type— alwaysDraftIssuefor this projectcontent.id— unique item content IDid— project item ID (this is theitemIdin project board URLs)status— column name (e.g.,Todo,In Progress,Done)title— same ascontent.title
Find a specific item
By title keyword:
gh project item-list 2 --owner cherchyk --format json --limit 50 | jq '.items[] | select(.title | test("browser_navigate_history"; "i"))'
By project board URL itemId:
The itemId in URLs like ?itemId=171559730 maps to the id field in the JSON output.
Map branch names to items
Branch names follow the pattern feature/<number>-<short_name>. The number is not a GitHub issue number — it's a project board sequence. Match by the <short_name> portion against item titles.
Example: branch feature/9-browser_navigate_history → search for items with title containing "browser_navigate_history".
Work Item Structure
Each draft issue body contains a structured spec with:
- Priority / Status / Effort — metadata
- Description — what the feature does
- Architecture — files to create/modify, response classes, patterns
- Tool definition (inputSchema) — JSON Schema for MCP tool parameters
- Implementation — pseudocode or detailed steps
- Test file — where tests should go
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 · 76 lines · 43 tokens per session scan A 45d148de2b49
project-workitems is an agent published in the GitHub repository cherchyk/MCPBrowser (8 stars, last pushed 21d ago), licensed MIT. It adds 43 tokens to every session and 736 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
Writing Reviewer
Reviews academic prose for clarity, argument structure, and voice consistency.
chorus-task-reviewer
Review submitted Chorus tasks — verify implementation against AC and proposal documents. Spawn via the blocking subagent tool after chorussubmitforverify.
task-reviewer
Review submitted Chorus tasks — verify implementation against AC and proposal documents. Spawn after chorussubmitforverify.
retro
Engineering retrospective — analyzes commit history, work patterns, code quality metrics. Per-person breakdowns, shipping streaks, actionable improvements. READ-ONLY, never modifies code.
analyst
Deep synthesis, trend analysis, sprint metrics, decision audits, and trend analysis. Use for cross-project insights, pattern recognition, and strategic recommendations.
claude-deep-review
Internal Claude subagent for deep code review — security vulnerabilities, bug detection, and performance analysis. Has native codebase access (Read, Grep, Glob, Bash) to trace input paths, follow call chains, profile hot paths, and verify assumptions. Launched automatically by council review workflows — not invoked…