Borrowing it
Nothing to install: this file belongs to leshchenko1979/fast-mcp-telegram. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/leshchenko1979/fast-mcp-telegram/master/.cursor/skills/release-notes/SKILL.mdgit clone --depth 1 https://github.com/leshchenko1979/fast-mcp-telegramWrote 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/leshchenko1979/fast-mcp-telegram/release-notes)<a href="https://agentmods.dev/skills/leshchenko1979/fast-mcp-telegram/release-notes"><img src="https://agentmods.dev/badge/skills/leshchenko1979/fast-mcp-telegram/release-notes/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/leshchenko1979/fast-mcp-telegram/release-notes"><img src="https://agentmods.dev/badge/skills/leshchenko1979/fast-mcp-telegram/release-notes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 83 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00041 | $0.01955 |
| Opus 5 | $0.00020 | $0.00978 |
| Sonnet 5 | $0.00008 | $0.00391 |
| Haiku 4.5 | $0.00004 | $0.00196 |
Grade A, and why
Release Notes Generation 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 9d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- Release Notes Generation — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release Notes Generation
Mandatory workflow for fast-mcp-telegram releases. Release notes belong on GitHub only — never commit RELEASE_NOTES*, temp note files, or similar to git.
Workflow overview
- Memory bank + git on
master→ user-facing diff analysis - Update docs (section 3) if needed
- Classify scope (section 4) → draft notes (section 5) → review gate when required
uv version→ commit → tag → push →gh release create→gh release view- Verify CI/checks green on release tag or master commit (section 6 gate)
- Telegram HTML (section 7) only after release is published and CI is green (or user explicitly overrides)
1. Context
Memory bank — completed work since last release:
cat .cursor/memory-bank/progress.md
cat .cursor/memory-bank/activeContext.md
Focus on dated entries; cross-check with git.
Git since last major tag (X.Y.0):
git tag --sort=-version:refname | grep -E '^[0-9]+\.[0-9]+\.0$' | head -1
git log --oneline <last-major-tag>..HEAD
git log --oneline --all --graph --decorate | head -40
Only include changes merged to master (memory bank may mention other branches). Merge memory bank summaries with git analysis. Prepare notes before creating the new tag.
2. User-facing analysis
End-user impact only:
git diff <previous-major-tag>..HEAD
git log --oneline <previous-major-tag>..HEAD
git show HEAD:<file> # final state when needed
Treat commit messages as hints; validate against actual behavior. Describe what users can do, not implementation.
Prioritization for notes:
- Primary: new features, fixes, behavior changes
- Omit: refactoring and internal cleanup unless they are the only changes (still complete docs per section 3)
- Grafana, telemetry, and ops dashboards are internal/ops tooling — never user-facing. Omit from release notes unless they are the only changes.
- Fixes vs new work: Fixes that pertain to features introduced in this release go under New Features only — never under Fixes. Fixes = regressions in previously existing features or unrelated bugs. If a new feature has bugs, it's not a "fix" for users, it's just the feature being completed.
- Dependencies: User-visible stack milestones (e.g. FastMCP 3.x) go under New Features.
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.
- 9d ago First seen · 179 lines · 41 tokens per session scan A e21ce065669b
Release Notes Generation is a skill published in the GitHub repository leshchenko1979/fast-mcp-telegram (49 stars, last pushed 15d ago), licensed MIT. It adds 41 tokens to every session and 1,955 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 2026-08-30.
Other skills, from other repositories
Finishing a Development Branch
Clean branch finalization, squashing commits, and updating changelogs before merging.
changelog
Changelog Generation Command 📝.
github-release-management
Comprehensive GitHub release orchestration with AI swarm coordination for automated versioning, testing, deployment, and rollback management.
release-cut
Cut a new pi-agent-dashboard release: promote ## [Unreleased] in CHANGELOG.md, bump every workspace package.json per SemVer, commit, tag v , and push — triggering the Release workflow that publishes every non-private workspace, builds the Electron artifacts, and creates a GitHub Release. Use on "cut a release"…
public-plugin-packaging
Use when packaging an Agentlas agent repo for public GitHub release, Codex plugin submission, Claude adapter distribution, or one-line terminal installation.
release-revoke
Revoke or rollback a pi-agent-dashboard release: delete the GitHub Release, remove the git tag locally and on origin, deprecate the npm version (npm unpublish is blocked after 72h), and optionally revert the release commit. Use when the user says "revoke release", "rollback release", "delete release", "unpublish…