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/0langa/cibseven-devflows/releasegit clone --depth 1 https://github.com/0langa/cibseven-devflowsWhat 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 | $0.00015 | $0.00388 |
| Opus 5 | $0.00008 | $0.00194 |
| Sonnet 5 | $0.00003 | $0.00078 |
| Haiku 4.5 | $0.00002 | $0.00039 |
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 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.
What it actually says
Release version $1 of the repository in the current working directory through the
cibseven-devflows release process.
Follow the release-with-devflows skill exactly:
- Call
doctorwith the repository path. Fix whatever is notok- deploy the process or the decision withdeploy_processif either is missing - before going on. - Show the gates with
list_gates. - Start a dry run with
start_release(repo_path, "$1", dry_run=true). - Poll
get_runand show me the gate report. - Then handle whichever of the two outcomes happened:
- No task appeared and the run has finished. The DMN policy auto-approved it. Do not wait
for an approval that will never come: report
policy.policy_reasonso I know why nobody was asked. - A task is open. Show me the gate report, the drafted
release_notesandnotes_source, then stop and ask me before callingapprove_gate. Do not approve on your own judgement. If I want different notes, tell me to edit them in the web UI form -approve_gatecannot send them.
- No task appeared and the run has finished. The DMN policy auto-approved it. Do not wait
for an approval that will never come: report
- Report
tag_name,release_urlandstatewhen the run ends. If the run is stuck, show theincidentsfromget_runand name the likely cause before suggestingretry_run.
Only start a real run (dry_run=false) if I passed --real and the dry run finished cleanly.
If I did not pass --real, finish after the dry run and tell me what the real run would do.
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 · 29 lines · 15 tokens per session scan A f49e43df39dd
release is a command published in the GitHub repository 0langa/cibseven-devflows (0 stars, last pushed 9d ago), licensed Apache-2.0. It adds 15 tokens to every session and 388 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.