Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add V-Songbird/slag/plugin install annealWrote 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/v-songbird/slag/repo-docs)<a href="https://agentmods.dev/skills/v-songbird/slag/repo-docs"><img src="https://agentmods.dev/badge/skills/v-songbird/slag/repo-docs/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/v-songbird/slag/repo-docs"><img src="https://agentmods.dev/badge/skills/v-songbird/slag/repo-docs.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 | $0.00170 | $0.01051 |
| Opus 5.5 | $0.00068 | $0.00420 |
| Sonnet 5.5 | $0.00034 | $0.00210 |
| Haiku 4.5 | $0.00017 | $0.00105 |
Grade A, and why
repo-docs 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 4d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo docs
Make the maintained documentation agree with what the project actually does, make its development instructions usable by each intended host, and give a project one documentation policy to follow.
Argument: $ARGUMENTS. If the host leaves it literal, read the request instead. audit, a review request, an explicit no-edit instruction, or the command alone with no argument and no request beside it means report only: nothing is written in the project, and a report is saved only as the reconciliation's step 4 allows. fix, or an explicit reconciliation or cleanup request in the owner's words, authorizes ordinary in-scope documentation fixes. Resolve an ambiguous request as an audit, and end an audit by naming fix as the way to apply its ordinary fixes. maintain runs the maintenance step first and edits nothing until the owner approves a group of its proposals. adopt edits nothing until the owner approves the files it shows. readme, or a request about one README, works on that README alone. A request to write one page for people authorizes writing that page and works on it alone; a request to review one reports on that page alone. A path narrows the pass to that area plus its incoming references; state that boundary.
On Claude Code invoke /anneal:repo-docs; on Codex use $repo-docs; on Antigravity use /repo-docs. Find the plugin files through ${CLAUDE_PLUGIN_ROOT} on Claude Code, or resolve ../../ from this file on other hosts. Resolve target paths against the project root, never the installed plugin directory.
On Antigravity, give every command the project root the person named as its working directory, the Cwd of run_command. Without it, commands can run in Antigravity's own scratch directory instead of the project. When the person named no project root, ask for it before running anything.
Modes
Every mode reads the Invariants section of the documentation contract first, and treats the project's own applicable instructions as its documentation policy.
What ships with it
10 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.
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.
- 4d ago Changed · -1 lines · -3 tokens per session 50d49fc0f77f
- 5d ago Changed · -1 lines · -20 tokens per session b651f81ca711
- 9d ago Changed · +6 lines · -8 tokens per session 20cd76023c8e
- 10d ago First seen · 45 lines · 201 tokens per session scan A 08956ec7d11e
repo-docs is a skill published in the GitHub repository V-Songbird/slag (1 stars, last pushed today), licensed MIT. It adds 170 tokens to every session and 1,051 once invoked, about $0.0007 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 2026-11-04.
repo-docs compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| repo-docsV-Songbird/slag | Skill | 1 | today | MIT | A | 170 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 135k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 100k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 80k | 8d ago | MIT | A | 200 | Claude Code, Codex |
| next-cache-components-adoptionvercel/next.js | Skill | 144k | today | MIT | A | 95 | Claude Code |
| chat-pet-sprite-creationmicrosoft/vscode | Skill | 195k | today | MIT | A | 53 | Claude Code, Codex |