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 agent-referencesgit 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/agent-references)<a href="https://agentmods.dev/skills/dean0x/devflow/agent-references"><img src="https://agentmods.dev/badge/skills/dean0x/devflow/agent-references/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/agent-references"><img src="https://agentmods.dev/badge/skills/dean0x/devflow/agent-references.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00017 | $0.00561 |
| Opus 5.5 | $0.00007 | $0.00224 |
| Sonnet 5.5 | $0.00003 | $0.00112 |
| Haiku 4.5 | $0.00002 | $0.00056 |
Grade A, and why
agent-references 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.
How it starts
The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent References
Iron Law
READ BY EXPLICIT PATH ONLY; NEVER PRELOAD
An agent or command that owns a file here names its full path in its own body and reads it with the Read tool when its mode or branch needs it. No agent
skills:list, no pluginrequires:and no preload names this skill: a preload would put every file in every spawn and undo the saving.
Files
Path under references/ |
Owner | Read when |
|---|---|---|
synthesize/{mode}.md |
Synthesize | The prompt's Mode: line names {mode} |
curate/maintain.md |
Curate | claim-due hands out at least one entry |
commands/{name}.md |
The command named in the file | The command's condition for that branch holds |
The installed directory is {claude_dir}/skills/devflow:agent-references/, where {claude_dir} is Claude Code's directory: CLAUDE_CONFIG_DIR when that is set to an absolute path, else $HOME/.claude.
The model never invokes this skill: disable-model-invocation: true keeps it out of the
model's own skill choices, and user-invocable: false keeps it out of the slash menu.
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/commands/code-review-levels.md 1.3 KB
- references/commands/implement-evidence-asks.md 4.6 KB
- references/commands/implement-revalidate.md 1.4 KB
- references/commands/plan-levels.md 4.0 KB
- references/curate/maintain.md 4.2 KB
- references/synthesize/bug-analysis.md 2.7 KB
- references/synthesize/design.md 1.5 KB
- references/synthesize/exploration.md 969 B
- references/synthesize/planning.md 2.0 KB
- references/synthesize/research.md 2.0 KB
- references/synthesize/review.md 3.7 KB
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 Changed · +4 lines 36855ba677f6
- 2d ago Changed 1c8c15eb49bb
- 3d ago Changed · +4 lines d353db14c4fb
- 4d ago First seen · 34 lines · 17 tokens per session scan A b90c552776f8
agent-references 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 561 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 2026-10-13.
Other skills, from other repositories
reflect
Use Recall Reflect to review AI coding workflow history as a conversation-first timeline and discuss observed patterns before changing behavior. Trigger when the user asks to reflect on a project, review AI coding workflow, inspect workflow friction, discuss repeated corrections, review handoffs, or explore possible…
guard
Protect Claude Code sessions from context overflow by running a background daemon that monitors session size and auto-prunes before compaction hits. Use when the user says "guard", "protect session", "context getting long", "prevent compaction", "session management", or is running agent teams that need continuous…
totem-compiled-rules
Compiled architectural rules and lessons from the Totem knowledge base. Load this when reviewing code for pattern violations or architectural drift.
setup-obsidian
Turn a repo's markdown docs folder into a searchable retrieval graph — router, generated indexes, state file — and open it as an Obsidian vault.
continuity-brief
Start a session knowing what the last one did and decided. Use when the task involves: session start, what did i do last, wake up, continuity, resume, brief.
context-checkpoint
Summarise, pin what matters, drop the noise, keep going. Use when the task involves: checkpoint, compact, context, summarize, phase, long session.