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/paruff/ufawkesai/releasegit clone --depth 1 https://github.com/paruff/uFawkesAIWhat 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 | $0.00060 | $0.00912 |
| Opus 5 | $0.00030 | $0.00456 |
| Sonnet 5 | $0.00012 | $0.00182 |
| Haiku 4.5 | $0.00006 | $0.00091 |
Grade A, and why
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 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent: Release
Invoke when: Tests passing + review approved on a releasable increment. DORA: AI Capability 4 (Strong version control) + Core: Continuous Delivery Token cost: Low–Medium Output: Published release + dev.to draft + LinkedIn draft + ufawkes.dev update
Purpose
Execute the "one new thing a week" release cycle as a checklist — not a creative
decision each time. This agent is a thin trigger: the write-once-ship-four-times
checklist (triage → document → tag/publish → dev.to → LinkedIn → ufawkes.dev),
semver rules, and minimum-shippable-increment rule live in the release skill —
this file only defines when to run, what to check first, and what to hand off
afterward (which the skill doesn't know about).
Trigger Conditions
| Trigger | Description |
|---|---|
| Weekly cadence | Thursday: if increment is shippable, release it |
| Feature complete | All acceptance criteria from discovery-brief.md met |
| Hotfix | Change failure rate event resolved, patch ready |
| Documentation release | No code change required — doc, Dojo lab, or decision post counts |
Pre-conditions
- Load
releaseskill:"load release skill" - All tests passing (test agent report:
status: pass) - Review approved (review agent report:
status: approved) - delivery agent report:
deployment_readiness: true(for infra changes) - CHANGELOG.md exists in the target repo
-
ghCLI authenticated:gh auth status - Target repo and version confirmed:
REPO=paruff/REPO_NAME,VERSION=v0.x.y
Responsibilities
Run the release checklist (delegate to skill)
Follow the release skill's Phase 1–6 checklist in full: triage open issues and
blockers, document (CHANGELOG + README Status), tag and publish the GitHub Release,
draft the dev.to post, draft the LinkedIn post, and update the ufawkes.dev stack
page. Use that skill's semver decision table and minimum-shippable-increment rule
to resolve any judgment calls — do not re-derive them here.
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 · 88 lines · 60 tokens per session scan A 214f1fb6e2fe
release is an agent published in the GitHub repository paruff/uFawkesAI (2 stars, last pushed 10d ago), licensed MIT. It adds 60 tokens to every session and 912 once invoked, about $0.0003 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
ijfw-release-eng
Ships releases: version bump, tag, CI publish watch, rollback if smoke fails. Trigger when phase passes ship-gate.
mcp-release-manager
Prepares versioning and release changes for the mcp-linear package and publish workflow.
agents-memory-updater
Mine high-signal transcript deltas, update local continual-learning-memory.json, and keep the incremental transcript index in sync. Never write Learned sections to root AGENTS.md.
GitHub
Executive-tier agent owning all git and GitHub API write operations — commits, pushes, PR creation, issue updates, label management. Receives approved changes from any executive after Review APPROVED. The sole executor of remote writes in the fleet.
git-workflow
Manages git operations including branching, committing, PR creation, and release workflows. Use when preparing commits, creating PRs, managing branches, or handling merge conflicts. Enforces conventional commits and branch protection rules.
release
(stub) Capture project-specific guidance for release.