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 skills add saidsef/mcp-github-pr-issue-analyser --skill project-boardsgit clone --depth 1 https://github.com/saidsef/mcp-github-pr-issue-analyserWrote 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/saidsef/mcp-github-pr-issue-analyser/project-boards)<a href="https://agentmods.dev/skills/saidsef/mcp-github-pr-issue-analyser/project-boards"><img src="https://agentmods.dev/badge/skills/saidsef/mcp-github-pr-issue-analyser/project-boards.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 | $0.00028 | $0.01732 |
| Opus 5 | $0.00014 | $0.00866 |
| Sonnet 5 | $0.00006 | $0.00346 |
| Haiku 4.5 | $0.00003 | $0.00173 |
Grade A, and why
project-boards 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 7d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Boards
Read and change GitHub Projects (v2) boards: what is on one, what each card's fields say, and where an issue sits.
Prerequisites
project_ownerandproject_number, both readable from the board's URL:https://github.com/users/OWNER/projects/NUMBERorhttps://github.com/orgs/OWNER/projects/NUMBERrepo_owner,repo_nameandissue_numberfor the issue or pull request- A token that reaches Projects. This is a separate grant from
repo: a classic token needsread:projectto read andprojectto write, a fine-grained one needs Projects read and write
The board's owner is not always the repository's owner. An organisation board
holding issues from several repositories is the common case, so read
project_owner off the board URL rather than assuming it matches repo_owner.
Workflow
Filing an issue and placing it
- Call
create_issueas usual - Call
get_project_fieldsto see which fields the board has and what each single-select one accepts - Call
set_project_fieldwith the field and option names. It puts the issue on the board first if it is not already there, soadd_to_projectis only needed when no field is being set
Triaging a backlog
- Call
list_project_itemsto read every card with its field values - Group by the
fieldsmap, for example byStatus, to see what is where - Call
set_project_fieldper issue to move it
Taking something off
- Call
remove_from_project - The issue stays open and untouched. Only the card goes, and the field values it held go with it
- Ask the user in chat before removing a card, since the field values cannot be recovered
Tool Parameters
get_project_fields
| Parameter | Type | Description |
|---|---|---|
project_owner |
str | User or organisation that owns the board |
project_number |
int | Project number, as it appears in the board's URL |
Returns project_number, title, url and fields. Each field carries its
id, name, data_type and options. options is empty for anything that is
not a single select, which is what tells you set_project_field will refuse it.
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.
- 7d ago First seen · 165 lines · 28 tokens per session scan A c04ea1d99cee
project-boards is a skill published in the GitHub repository saidsef/mcp-github-pr-issue-analyser (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 28 tokens to every session and 1,732 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 2026-08-31.
Other skills, from other repositories
guardian-memory
Maintain project context in Project Guardian's memory.db knowledge graph. Use during coding, debugging, planning, and project-management sessions to restore relevant context and record significant decisions, changes, tasks, and milestones.
guardian-session
Restore relevant Project Guardian context from memory.db at session start. Use when resuming project work, switching repositories, or answering what was previously in progress; surface active tasks, open bugs, recent observations, and blockers.
atelier
Two-agent post-generation quality gate for vibe-coded applications. Deterministic, gradeable ruleset enforcing UI/UX design-system craft and backend architectural soundness.
session-handoff
Close out a work session on Arthur MCP by updating docs/HANDOFF.md and docs/ROADMAP.md and reporting which validation commands were run. Use at the end of a task, before telling the user work is complete.
mcp-dino
Skill "mcp-dino" from shennawardana23/mcp-dino, covering skill.md — dino-mcp development skills, skill: build & run, quick build (go only, uses existing ui), full build (vite ui + go) and run in dev mode (verbose).
quality
Evaluates whether a GitHub issue is spam, empty, needs more information, or is OK to proceed.