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/tdwhere123/do-it/do-it-corenpx skills add tdwhere123/do-it --skill do-it-coregit clone --depth 1 https://github.com/tdwhere123/do-itWhat 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 | $0.00041 | $0.00999 |
| Opus 5 | $0.00020 | $0.00500 |
| Sonnet 5 | $0.00008 | $0.00200 |
| Haiku 4.5 | $0.00004 | $0.00100 |
Grade A, and why
do-it-core 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Do-It Core
The protocol of record for universal execution behavior. The TSV owns the
canonical rule sentences and hook surfaces; this skill owns their human
workflow. Satellites cite core §<rule_id> instead of restating rules, and
validate:core-consistency blocks drift.
Tier definitions and capability selection stay in do-it-router. Claim-specific
closeout stays in do-it-verify. The baseline does not duplicate either
specialist.
Core Rules
- r-route — Pick the smallest tier that fits: Light mechanical, Standard work, Heavy boundary. Direct user intent wins over keyword labels. Counters: over-routing, under-routing, ceremony
- r-evidence — Work from evidence: read the files, diffs, and tests before claiming how the system works; label assumptions as assumptions, never as facts. Counters: silent-assumption, invented-api, contract-drift
- r-scope — Keep changes small: every edited line must trace to the request or its contracts; no speculative additions, abstractions, or unrelated fixes. Counters: scope-creep, collateral-change, needless-abstraction
- r-verify — Before any done, fixed, passing, ready, install, or merge claim: run the narrowest fresh check that exercises the changed path on this worktree and report its exact output; if proof is unavailable, state NOT_VERIFIED with the missing check and next action. Counters: unverified-claim, dishonest-green, irrelevant-verification
- r-uncertainty — Ask the user only when ambiguity changes correctness, safety, or user intent; resolve low-risk ambiguity from evidence using the narrowest reasonable interpretation. Counters: low-risk-paralysis, unattended-guessing
- r-boundary — Respect the action boundary: answer, review, diagnose, or plan authorizes no edits; external, destructive, or irreversible actions need explicit confirmation first. Counters: action-scope-expansion, implicit-destructive-authorization, publication-expansion
- r-report — Report what changed, what was verified, and what remains unverified; name anything dropped, deferred, or reinterpreted. Counters: dropped-requirements, process-noise
- r-recovery — On failure: diagnose before widening the change; three failed patches mean question the design, not try a fourth. Counters: thrashing, cover-up-edit
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 First seen · 74 lines · 41 tokens per session scan A d101305592ef
do-it-core is a skill published in the GitHub repository tdwhere123/do-it (27 stars, last pushed 21d ago), licensed MIT. It adds 41 tokens to every session and 999 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 2026-08-30.
Other skills, from other repositories
agent-quorum-manager
Agent skill for quorum-manager - invoke with $agent-quorum-manager.
agent-project-board-sync
Agent skill for project-board-sync - invoke with $agent-project-board-sync.
agent-release-manager
Agent skill for release-manager - invoke with $agent-release-manager.
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.
agent-repo-architect
Agent skill for repo-architect - invoke with $agent-repo-architect.
agent-pagerank-analyzer
Agent skill for pagerank-analyzer - invoke with $agent-pagerank-analyzer.