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/t-rav/hydraflow/hf.adrgit clone --depth 1 https://github.com/T-rav/hydraflowWrote 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/t-rav/hydraflow/hf.adr)<a href="https://agentmods.dev/commands/t-rav/hydraflow/hf.adr"><img src="https://agentmods.dev/badge/commands/t-rav/hydraflow/hf.adr.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 | $0.00000 | $0.00472 |
| Opus 5 | $0.00000 | $0.00236 |
| Sonnet 5 | $0.00000 | $0.00094 |
| Haiku 4.5 | $0.00000 | $0.00047 |
Grade A, and why
hf.adr 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 3d 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
Create ADR Draft Issue
Capture an architectural decision as a draft ADR issue routed into HydraFlow.
Usage
/hf.adr Adopt a single source of truth for pipeline queue counts
/hf.adr Move visual validation into merge worker gate
$ARGUMENTS should be the ADR title suffix. If empty, ask for one.
Instructions
Phase 0: Resolve Configuration
Before creating anything, resolve:
REPO:echo "$HYDRAFLOW_GITHUB_REPO"; if empty, usegit remote get-url originand parseowner/repo.ASSIGNEE:echo "$HYDRAFLOW_GITHUB_ASSIGNEE"; if empty, use repo owner.LABEL: Usehydraflow-find.
Never pass empty values to gh issue create.
Phase 1: Build ADR Issue
Create title: [ADR] <title from $ARGUMENTS>.
Create body with required sections:
## Context
<what problem/constraints drove this decision>
## Decision
<the concrete architectural decision>
## Consequences
<tradeoffs, follow-up work, operational impact>
Optional sections when relevant:
## Alternatives considered## Related
Phase 2: Create Issue with gh
Use --body-file to avoid escaping issues:
BODY_FILE=$(mktemp)
cat > "$BODY_FILE" <<'ADR_EOF'
## Context
...
## Decision
...
## Consequences
...
ADR_EOF
gh issue create --repo "$REPO" \
--assignee "$ASSIGNEE" \
--label "$LABEL" \
--title "[ADR] <title>" \
--body-file "$BODY_FILE"
rm -f "$BODY_FILE"
Phase 3: Report Back
Return:
- created issue URL
- resolved repo/assignee/label
- one-line ADR summary
- confirmation it is queued for pipeline processing (triage -> plan/implement -> review)
Notes
- ADR formatting is validated by HydraFlow ADR routing logic.
- Use
hydraflow-findso the issue is queued into the pipeline. - Keep decision text concrete and implementation-actionable.
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.
- 3d ago First seen · 89 lines · 0 tokens per session scan A f261b5a842f4
hf.adr is a command published in the GitHub repository T-rav/hydraflow (5 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 472 tokens. 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
ledger-plan
Generate implementation plan with backlog, milestones, and test plan constrained by decisions and risks.
portfolio
Show a read-only hub-wide portfolio of canonical Ideas and active Projects without duplicating topic-owned records.
cycle-design
Design a cycle — create new cycles with planned stories, detail existing planning cycles, or quick-sketch a roadmap. Detects planning docs in .craft/planning/ and sources the cycle from them when relevant.
cycle-start
Activate a cycle and start implementing its stories.
story-archive
Move a story from a cycle back to the backlog.
project
Manage projects inside a topic wiki. Projects are folders under output/projects/ that group related outputs (playbooks, images, code, data) with a goal captured in WHY.md.