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 skills/bnet47/codexicon/retronpx skills add bnet47/codexicon --skill retrogit clone --depth 1 https://github.com/bnet47/codexiconWhat 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 | $0.00034 | $0.00397 |
| Opus 5 | $0.00017 | $0.00198 |
| Sonnet 5 | $0.00007 | $0.00079 |
| Haiku 4.5 | $0.00003 | $0.00040 |
Grade A, and why
retro 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.
What it actually says
Retro
Announce: "I'm using retro to step back and assess direction."
1. Load evidence
Read the relevant charter/spec, plan, checkpoints, accepted decisions, current diff, and verification state. Note missing or empty evidence rather than inferring a history that is not recorded.
2. Assess
Answer with concrete evidence:
- Direction: Is the original problem and outcome still correct? Has scope moved away from it?
- Execution: What completed cleanly, blocked, or required rework, and why?
- Decisions: Which assumptions or ADRs no longer fit the evidence?
- Debt: What shortcut or ambiguity creates the largest future risk?
- Workflow: Did planning, context management, or delegation improve outcomes or add overhead?
3. Report
# Retro: [Project or feature] — [YYYY-MM-DD]
## Working
- [Evidence-backed strength.]
## Not working
- [Evidence-backed problem.]
## Scope drift
- [Original intent versus current state.]
## Decisions to revisit
- [ADR or assumption.]
## Recommended changes
1. [Highest-leverage action.]
## Verdict
CONTINUE | STOP | PIVOT
[Rationale and immediate next move.]
Save to agent_docs/sessions/[YYYY-MM-DD]-[slug]-retro.md when a durable report is useful or requested.
4. Act only within authority
Continue ordinary in-scope implementation when the verdict is CONTINUE and the request includes it. For STOP or PIVOT, recommend the appropriate spec, ADR, or plan updates and perform them only when already authorized. Never auto-commit, push, open a PR, or rewrite accepted ADRs as a retro side effect.
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 · 55 lines · 34 tokens per session scan A 3c9ffd565c29
retro is a skill published in the GitHub repository bnet47/codexicon (5 stars, last pushed 3d ago), licensed MIT. It adds 34 tokens to every session and 397 once invoked, about $0.0002 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 skills, from other repositories
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
dingtalk_channel_connect
Use a headed browser to automatically complete DingTalk channel integration for QwenPaw. Applicable when the user mentions DingTalk, developer console, Client ID, Client Secret, bot, Stream mode, binding or configuring a channel. Supports pausing when a login page is detected and resuming after the user logs in.
当用户需要对PDF文件进行任何操作时，请使用此技能。包括从 PDF 中读取或提取文本/表格、合并多个 PDF、拆分 PDF、旋转页面、添加水印、创建新PDF、填写PDF表单、加密/解密 PDF、提取图片，以及对扫描版 PDF 进行 OCR 使其可搜索。如果用户提到 .pdf 文件或要求生成 PDF，请使用此技能。.
make_plan
For external plan request scenarios, guides the Agent to request a clear, actionable, step-by-step plan from a stronger Agent via listagents and chatwithagent, emphasizing that the plan is executed by the requester, not by the consulted Agent.
oma-scholar
Scholarly research companion using Knows sidecar spec (.knows.yaml). Generates, validates, reviews, queries, and compares structured research-paper sidecars, and fetches them from knows.academy. Use for academic literature search, survey synthesis, paper authoring assistance, and peer review with token-efficient…
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.