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 api-requestsgit 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/api-requests)<a href="https://agentmods.dev/skills/saidsef/mcp-github-pr-issue-analyser/api-requests"><img src="https://agentmods.dev/badge/skills/saidsef/mcp-github-pr-issue-analyser/api-requests/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/skills/saidsef/mcp-github-pr-issue-analyser/api-requests"><img src="https://agentmods.dev/badge/skills/saidsef/mcp-github-pr-issue-analyser/api-requests.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 | $0.00037 | $0.02252 |
| Opus 5.5 | $0.00015 | $0.00901 |
| Sonnet 5.5 | $0.00007 | $0.00450 |
| Haiku 4.5 | $0.00004 | $0.00225 |
Grade A, and why
api-requests 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 yesterday.
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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
API Requests
Four tools reach any GitHub endpoint that the other tools do not cover.
github_search_api_routes finds the REST route for a task. The other three send
the request, one tool per kind of change, so a client can tell a read from a write
from a deletion before anything is sent. They return GitHub's reply as text. The
other tools trim that reply and handle GitHub's quirks, and these four do neither.
When to use them
Use another tool wherever one covers the task:
| Task | Tool |
|---|---|
| Read a file or a directory | github_get_repository_file, github_list_repository_tree |
| List or delete branches | github_list_branches, github_delete_branch |
| Commit files to a branch | github_commit_files |
| Read workflow runs and job logs | github_get_workflow_runs, github_get_job_log |
| Label a pull request | github_update_pr, since GitHub keeps PR labels on the issues endpoint |
| List an owner's repositories | github_list_repos, which picks the user or organisation endpoint itself |
Reach for these four for the rest, such as collaborators, repository settings, rulesets, webhooks, commit comparisons, or a GraphQL field no tool selects.
Which tool sends what
| Tool | Kind | REST | GraphQL | Scope |
|---|---|---|---|---|
github_search_api_routes |
read | Searches the route list and sends nothing | - | none |
github_api_read |
read | GET |
A query | none |
github_api_write |
write | POST, PATCH, PUT |
A mutation, unless it deletes or removes something | repo |
github_api_delete |
destructive | DELETE |
A mutation that calls a delete... or remove... field |
repo |
A grant without repo does not list github_api_write or github_api_delete at all.
Each request tool refuses a call that belongs to another, so its hint stays true.
github_api_read refuses any mutation, and github_api_write refuses a mutation
that calls a delete... or remove... field. Some POST, PATCH and PUT routes
still overwrite data, such as PUT /repos/{owner}/{repo}/topics, which replaces every
topic. Read the route's summary before calling 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.
- yesterday First seen · 171 lines · 37 tokens per session scan A 947544c37096
api-requests is a skill published in the GitHub repository saidsef/mcp-github-pr-issue-analyser (6 stars, last pushed 2d ago), licensed Apache-2.0. It adds 37 tokens to every session and 2,252 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-11-05.
api-requests compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| api-requestssaidsef/mcp-github-pr-issue-analyser | Skill | 6 | 2d ago | Apache-2.0 | A | 37 | Claude Code, Codex |
| td-api-referencedylanroscover/Embody | Skill | 212 | yesterday | MIT | A | 48 | Claude Code |
| manage-annotationsdylanroscover/Embody | Skill | 212 | yesterday | MIT | A | 28 | Claude Code |
| watchINo-xious/stockbit-mcp | Skill | 57 | 3d ago | MIT | A | 88 | Claude Code |
| stockbit-statusINo-xious/stockbit-mcp | Skill | 57 | 3d ago | MIT | A | 70 | Claude Code |
| stockbit-authINo-xious/stockbit-mcp | Skill | 57 | 3d ago | MIT | A | 63 | Claude Code |
| bandar-checkINo-xious/stockbit-mcp | Skill | 57 | 3d ago | MIT | A | 54 | Claude Code |