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-orientgit 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-orient)<a href="https://agentmods.dev/skills/aahlijia/dekko/dekko-orient"><img src="https://agentmods.dev/badge/skills/aahlijia/dekko/dekko-orient/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-orient"><img src="https://agentmods.dev/badge/skills/aahlijia/dekko/dekko-orient.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 | $0.00100 | $0.02118 |
| Opus 5 | $0.00050 | $0.01059 |
| Sonnet 5 | $0.00020 | $0.00424 |
| Haiku 4.5 | $0.00010 | $0.00212 |
Grade A, and why
dekko-orient scanned grade A with 1 finding 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 9d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
import (e.g. `requests.get`) to find in-repo call sites, rather than How it starts
The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orienting with dekko (read less of the repo)
A repo with a .dekko/ directory is already parsed and indexed. Call
dekko's MCP tools (mcp__dekko__*) or CLI before grepping for a
symbol or reading a whole file — that is the token cost this skill
exists to avoid. If mcp__dekko__* tools don't show up in your
toolset yet, they may be deferred behind a tool search — search for
"dekko" before falling back to Read/Grep, don't give up after one miss.
No .dekko/ directory yet? Run dekko map . (or the /map command)
once, then use the tools below.
When to reach for dekko vs. grep/Read
| Need | Use | Not |
|---|---|---|
| You know what the code does but not its exact name/spelling | search_code |
grepping guessed keywords across every file |
| A symbol's signature, doc, or its callers/callees | query_symbol, get_callers, get_callees |
grep for the name |
| Which in-repo symbols reference an external/third-party name (a library import, not a local symbol) | find_usages |
grepping the import name across every file |
| A file or directory's shape | outline |
reading the whole file |
| Everything needed to work a diff or symbol | workset |
assembling outlines + packs by hand |
| Tests a change impacts | impacted_tests |
guessing from filenames |
| Whether the map on disk is stale, and fixing it without shell access | map_status, refresh_map |
assuming the map is current; shelling out to dekko map when only MCP tools are available |
| Text dekko doesn't model — strings, comments, config, prose | grep/Read | — |
search_code in particular replaces the "grep for a few plausible
keywords and hope" impulse: it's BM25-style relevance over symbol
names, signatures, and doc lines (not substring matching), so it
finds the right symbol even when your guessed keyword isn't literally
in the source. Reach for it first whenever the task is phrased as
behavior ("where do we retry failed requests?") rather than a known
identifier.
Orient first
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.
- 9d ago First seen · 156 lines · 100 tokens per session scan A 33d021b9b87b
dekko-orient is a skill published in the GitHub repository aahlijia/dekko (3 stars, last pushed 8d ago), licensed MIT. It adds 100 tokens to every session and 2,118 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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".
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.
github-cli
GitHub CLI (gh) wrapper for PR status, issues, and repository operations.