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/zookanalytics/gc-toolkit/filing-documentationnpx skills add zookanalytics/gc-toolkit --skill filing-documentationgit clone --depth 1 https://github.com/zookanalytics/gc-toolkitWhat 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 | $0.00084 | $0.00515 |
| Opus 5 | $0.00042 | $0.00258 |
| Sonnet 5 | $0.00017 | $0.00103 |
| Haiku 4.5 | $0.00008 | $0.00052 |
Grade A, and why
filing-documentation 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
Filing Documentation
A decision procedure for where a durable document goes, applied at the
moment you write it. The full conventions — the two tiers, bead-keyed
naming, the no-archiving rule, frontmatter — live in the gc-toolkit
pack's docs/file-structure.md (at the repo root, not under this skill
directory), which is the authority. This skill applies those rules at
write-time; it is not a second copy of them.
1. Is this a committed file at all?
A durable analysis, decision record, research synthesis, or spec is a repo artifact — commit it. Ephemeral status, or a note that only coordinates the task while it is in flight, can stay a bead comment.
The line that matters: a durable document must never live only as a bead comment. Bead comments are operational state, not the record. If someone would want to read it after the bead closes, it is a file.
2. Which tier?
- Authoritative — what's true now, that someone owns keeping current
→
docs/<topic>.md. - A record of work — what was thought, decided, or explored on a bead
→
specs/<bead-id>/.
Unsure? Ask which claim the document makes. What is true is central;
what was considered while doing this bead is local. The gc-toolkit
pack's docs/file-structure.md carries the tier rules in full, including
the bead-ID-alone directory naming.
3. Commit it
Write the file on your work branch and commit it with the rest of your work. That commit is what makes it durable and reviewable — the point of step 1.
For anything past this procedure — directory naming, frontmatter,
timestamps, cross-doc references, the no-archiving rule — read the
gc-toolkit pack's docs/file-structure.md (at the repo root).
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 · 46 lines · 84 tokens per session scan A 642bb9793979
filing-documentation is a skill published in the GitHub repository zookanalytics/gc-toolkit (5 stars, last pushed 4d ago), licensed MIT. It adds 84 tokens to every session and 515 once invoked, about $0.0004 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.
hedging-strategy
Hedging strategy design (beta hedge / option protection / tail risk / cross-asset hedging), including hedge-ratio calculation and cost evaluation.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
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…
oma-hwp
Convert HWP / HWPX / HWPML files to Markdown using kordoc. Extracts text, headings, tables, lists, images, footnotes, and hyperlinks. Use for Korean word processor files (Hangul), government documents, and AI-ready data preparation.
error-recovery
Standard recovery patterns for all squad agents. When something fails, adapt — don't just report the failure.