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 commands/marcusgoll/spec-flow/announce-releasegit clone --depth 1 https://github.com/marcusgoll/Spec-FlowWrote 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/commands/marcusgoll/spec-flow/announce-release)<a href="https://agentmods.dev/commands/marcusgoll/spec-flow/announce-release"><img src="https://agentmods.dev/badge/commands/marcusgoll/spec-flow/announce-release.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 | $0.00016 | $0.00944 |
| Opus 5 | $0.00008 | $0.00472 |
| Sonnet 5 | $0.00003 | $0.00189 |
| Haiku 4.5 | $0.00002 | $0.00094 |
Grade A, and why
announce-release scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
This command delegates to the x-announcement skill which:
- Generates engaging post from CHANGELOG
- Gets user confirmation before posting
- Posts main announcement via API
- Replies with GitHub release link in thread
- Handles errors gracefully without blocking
-
Invoke x-announcement skill via Skill tool:
- Pass version number
- Let skill handle entire workflow (generate → confirm → post → reply)
-
Skill workflow will:
- Extract highlights from CHANGELOG for version
- Show preview with character count
- Get user confirmation (post/edit/skip)
- Post to X API if approved
- Poll for tweet ID
- Reply with GitHub link
- Display both tweet URLs
-
Handle skill completion:
- Success: Display tweet URLs
- Failure: Show manual posting fallback
- Skip: Continue without announcement
<version_detection> If version argument provided:
VERSION="$ARGUMENTS" # e.g., "2.7.0"
If no argument (detect latest):
# Try git tag first
VERSION=$(git describe --tags --abbrev=0 2>/dev/null | sed 's/^v//')
# Fallback to CHANGELOG
if [ -z "$VERSION" ]; then
VERSION=$(grep -m 1 "^## \[" CHANGELOG.md | grep -oP '\[\K[^\]]+')
fi
# Validate version found
if [ -z "$VERSION" ]; then
echo "❌ Could not detect version. Specify manually:"
echo " /announce-release 2.7.0"
exit 1
fi
</version_detection>
<success_criteria>
- Version number detected or validated
- x-announcement skill invoked successfully
- User confirmation obtained before posting
- X announcement posted (or gracefully skipped)
- GitHub link reply posted in thread (or manual fallback provided)
- Tweet URLs displayed to user
- Release workflow unblocked on any X announcement failure </success_criteria>
📱 Generating X announcement for v2.7.0...
[Preview shown, user confirms]
📤 Posting to X... ✅ Posted!
Main Post: https://x.com/username/status/1234567890
GitHub Link Reply: https://x.com/username/status/1234567891
**Example 2: Announce specific version**
```bash
/announce-release 2.6.0
Example 3: User skips announcement
[Preview shown]
Options:
1. ✅ Post as-is
2. ✏️ Edit post text
3. ❌ Skip X announcement
[User selects 3]
X Announcement Skipped
Generated post text (for reference):
...
To post manually later: https://x.com/compose
Example 4: API unreachable
⚠️ X Poster API Unavailable
Generated post text:
...
Manual posting option:
1. Copy the post text above
2. Post manually to X: https://x.com/compose
3. Reply with: 🔗 Release notes: https://...
<anti_patterns> Avoid:
- ❌ Blocking on X announcement failures
- ❌ Posting without user confirmation
- ❌ Exceeding 280 character limit
- ❌ Failing silently without fallback
- ❌ Exposing API credentials or URLs publicly
Correct:
- ✅ Always get user confirmation before posting
- ✅ Validate character count before submission
- ✅ Provide manual posting fallback on errors
- ✅ Continue gracefully on any failure
- ✅ Keep API details internal-only </anti_patterns>
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.
- 4d ago First seen · 155 lines · 16 tokens per session scan A 486de6dc73a8
announce-release is a command published in the GitHub repository marcusgoll/Spec-Flow (92 stars, last pushed 4mo ago), licensed MIT. It adds 16 tokens to every session and 944 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 2026-08-30.
Other commands, from other repositories
quick-fix
Fast-track workflow for small bug fixes.
sync-linear
Sync current work with Linear ticket status.
review
Review the current diff for violations of the conventions in AGENTS.md and .cursor/rules/. Report findings ordered by severity; do not fix anything unless asked.
task-verify
PitWay: Run an inprogress task's approved verification command and persist evidence.
milestone-list
PitWay: List every milestone with a concise one-line status.
adv-gemini-research
Deep research query via Gemini with Google Search grounding.