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 skills add dean0x/devflow --skill apply-decisionsgit clone --depth 1 https://github.com/dean0x/devflowWrote 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/dean0x/devflow/apply-decisions)<a href="https://agentmods.dev/skills/dean0x/devflow/apply-decisions"><img src="https://agentmods.dev/badge/skills/dean0x/devflow/apply-decisions/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/dean0x/devflow/apply-decisions"><img src="https://agentmods.dev/badge/skills/dean0x/devflow/apply-decisions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00017 | $0.00580 |
| Opus 5.5 | $0.00007 | $0.00232 |
| Sonnet 5.5 | $0.00003 | $0.00116 |
| Haiku 4.5 | $0.00002 | $0.00058 |
Grade A, and why
apply-decisions 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.
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apply Decisions
Iron Law
VERBATIM IDs ONLY — NEVER FABRICATE
Cite only IDs that appear verbatim in DECISIONS_CONTEXT. If an ADR/PF ID is not in the index, do not cite it. If an entry looks relevant but you haven't Read its full body, do not cite it. Fabricated citations are worse than no citations.
DECISIONS_CONTEXT may be a slice; read the full index at the named path only when your work leaves the slice's scope.
5-Step Algorithm
Step 1: Scan the index
One line per active entry: its ID (ADR-NNN or PF-NNN), a title, then a status tag and/or, after —, its area or scope. A slice leads with (slice: N of M entries — full index: <path>).
Step 2: Identify plausibly-relevant entries
Pick entries whose title, area or scope overlaps the files you touch (a matching scope glob is a strong signal), the kind of issue or the architectural area. Follow up a cut-short title that looks relevant.
Step 3: Read the full body
Find the entry's heading in the file the footer names:
command grep -nF '## ADR-NNN:' "{worktree-from-footer}/.devflow/learning/decisions.md"
For a pitfall use ## PF-NNN: and pitfalls.md. Read with offset at the printed line and a limit of about 25, stopping at the next ## . The footer is the single source of truth for paths; the ledger is git-ignored, so search by shell. A verified date is the last confirmation; none means unconfirmed.
Step 4: Cite inline — in-session handoffs only
Cite applies ADR-NNN or avoids PF-NNN in-session only: your reasoning, prompts to downstream agents, your report back.
Anything committed, pushed or posted states the rule in words, never its ID (code, comments, tests, docs, commit messages, PR and issue text, review comments, and any report copied into those). IDs are numbered per machine, so no other clone can resolve one.
Step 5: Use verbatim IDs only
Cite only IDs in the index; never guess or rebuild one. When nothing clearly applies, cite nothing.
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 Changed · +2 lines d366f419e9d8
- 6d ago Changed 38a9bfe5bdc2
- 7d ago Changed · -70 lines · -28 tokens per session 49d6cca64936
- 10d ago Changed · +17 lines 623b1de66cb2
- 13d ago Changed · +3 lines · +12 tokens per session f115bed9f533
- 1mo ago First seen · 101 lines · 33 tokens per session scan A 811ee73ed450
apply-decisions is a skill published in the GitHub repository dean0x/devflow (20 stars, last pushed today), licensed MIT. It adds 17 tokens to every session and 580 once invoked, about $0.0001 per session on Opus 5.5. 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
find-simplifications
Use for a periodic repo-wide sweep of qwen-code for accumulated excess surface — dead components and files, orphaned locale keys, exports nothing consumes, added-then-removed scaffolding — filing candidates on a tracking issue and landing only what a maintainer has said yes to. Repo-wide and evidence-first; every…
swarm-pr-review
Run a graph-guided, tool-augmented PR review using context packing, parallel exploration, mandatory repository-agnostic risk-family coverage with dispatch scaled to diff size and risk, independent reviewer validation, critic challenge, and metrics writeback. Use for deep pull request review with low false-positive…
pr-review-canvas
Create a OpenBitFun Canvas for reviewing a pull request, branch diff, or change set with Cursor-style diff cards, review maps, risk callouts, and focused reviewer flow. Use when the user asks for a PR review canvas, diff walkthrough, change-set overview, or visual review summary.
code-review
You are a senior code reviewer. You receive diffs via stdin.
review
Adversarial fresh-context review and risk check of an increment before it ships; every finding cites path:line and is re-verified. Use for "review", "qa", "quality check", "critique this".
tech-debt-ci-review
Codex adapter for deep technical-debt and CI-stability audits. Use when asked to find test theater, flaky tests, missing or mis-scoped tests, brittle CI/toolchain behavior, structural debt blocking green PRs, or a remediation order for opencode-swarm.