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 aahlijia/dekko --skill dekko-delegategit clone --depth 1 https://github.com/aahlijia/dekkoWrote 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/aahlijia/dekko/dekko-delegate)<a href="https://agentmods.dev/skills/aahlijia/dekko/dekko-delegate"><img src="https://agentmods.dev/badge/skills/aahlijia/dekko/dekko-delegate/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/aahlijia/dekko/dekko-delegate"><img src="https://agentmods.dev/badge/skills/aahlijia/dekko/dekko-delegate.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 | $0.00127 | $0.01076 |
| Opus 5.5 | $0.00051 | $0.00430 |
| Sonnet 5.5 | $0.00025 | $0.00215 |
| Haiku 4.5 | $0.00013 | $0.00108 |
Grade A, and why
dekko-delegate 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 20d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Briefing subagents with dekko
The parent session was oriented at start-up; a subagent never is. It doesn't know the repo has a map, so it greps, reads whole files, and spends its first several thousand tokens rebuilding a picture the map already holds. Fix both halves in the prompt: give it the digest, and tell it to use the tools.
Procedure
-
Compute the digest once, scoped to the task. Run it in Bash and paste the output verbatim; don't summarize it by hand.
Agent's job Paste Budget Explore, answer questions, locate code dekko orient --budget 800~800 tokens; ~1200 on a repo with more than ~10 top-level directories Implement or review a change dekko workset [REV] --budget 2000(or--symbol <sym>), with--task "<what the agent must do>"1500-3000; the 6000 default is sized for the parent, not a brief Work on one symbol or file dekko context <sym> --budget 800ordekko outline <path>~800 Several agents on one subtree each one dekko orientfor all, plusdekko outline <dir>per agentorient once, outline ~500 each With no Bash, the MCP
summary(budget 800) orworksettools give the same digest; add the "Tools" paragraph below yourself, since onlydekko orientprints a steering preamble. -
Put the digest and the instructions in the prompt, under their own heading so the agent treats them as given, not as something to re-derive:
## Repo map (from dekko; already computed, do not redo) <pasted output> ## Tools This repo has a .dekko/ map. Use the dekko MCP tools (mcp__plugin_dekko_dekko__* or mcp__dekko__*; the dekko-orient skill applies) or `dekko <cmd>` in Bash, before any grep or whole-file Read: search_code to find code by what it does, outline for a file's shape, get_callers / impacted_tests for impact, get_context_pack with with_source for the lines to edit. Every tool regenerates a stale map itself; never run `dekko map` by hand, and never stop or kill dekko processes (`dekko serve --mcp`, `dekko daemon`): they belong to the parent session.
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.
- 20d ago First seen · 79 lines · 127 tokens per session scan A 66e62fadb1ad
dekko-delegate is a skill published in the GitHub repository aahlijia/dekko (5 stars, last pushed yesterday), licensed MIT. It adds 127 tokens to every session and 1,076 once invoked, about $0.0005 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 2026-09-27.
Other skills, from other repositories
roam
Codebase comprehension via roam-code CLI. Use when exploring codebases, planning modifications, debugging failures, assessing PR risk, or checking architecture health. Triggers on: understanding project structure, pre-change safety checks, finding symbols/files, blast radius analysis, affected tests, health scoring…
release-tag
Cut and publish a codeweb release end-to-end — prep the version/changelog file ecosystem, land it on main, push the vX.Y.Z tag, and let the tag-triggered workflow publish the GitHub Release. Use when asked to "cut a release", "tag a release", "publish vX.Y.Z", "do the release", or "ship version X".
codeweb
Inspect mapped callers and impact before changing code, find existing implementations before adding one, and review structural changes after an edit. Use during coding tasks; Codeweb product planning uses a separate workflow.
plan-schema
Plan file (.claude/plans/-plan.md) reference — sections, per-file format, dependency graph, and converter mappings.
beads-schema
Beads (bd CLI) reference — issue types, statuses, priorities, dependencies, and common commands.
prd-schema
Skill "prd-schema" from GantisStorm/essentials-claude-code, covering when to use, conversion from plans, schema, root object and user story object.