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 makifbaysal/tasktrooper --skill local-project-contextgit clone --depth 1 https://github.com/makifbaysal/tasktrooperWrote 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/makifbaysal/tasktrooper/local-project-context)<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/local-project-context"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/local-project-context/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/makifbaysal/tasktrooper/local-project-context"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/local-project-context.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 | $0.00045 | $0.01323 |
| Opus 5.5 | $0.00018 | $0.00529 |
| Sonnet 5.5 | $0.00009 | $0.00265 |
| Haiku 4.5 | $0.00005 | $0.00132 |
Grade A, and why
local-project-context 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 5d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Local Project Context
Overview
You run on a local developer machine, not in a CI/CD pipeline. There is no remote runner that will catch your mistakes later — the build and tests you run in your workspace are the only verification that happens before a human sees the result. Treat your workspace as production's last line of defense.
Core principle: Explore before you change; verify in this environment before you claim.
The environment
- Task workspace: each task is worked in a cloned checkout on its own branch. Your working directory is injected into the session context — always use it as the root, never assume paths from another task.
- Live codebase: your changes take effect immediately in the workspace. There is no separate deploy step for verification.
- No inherited state: if you build or test in this workspace, do it from scratch — never assume a prior session left a build artifact, a running server, or a seeded database.
Exploration tools (use before changing code)
| Tool | Use for |
|---|---|
codebase_search |
Concept/semantic search — "where is auth handled" |
grep_code |
Exact symbol/string — a function name, an error message |
get_repo_tree |
Structure and file layout of the repository |
get_symbol_skeleton |
A symbol's signature and outline without its full body |
expand_symbol_context |
Focused read of a symbol and its surroundings |
read_file |
Read a file with line numbers — up to 800 lines per call |
run_terminal |
Build, test, run the app, inspect output |
File tools (use instead of the shell for anything touching a file)
| Tool | Use for |
|---|---|
read_file |
Read with line numbers, whole file in one call |
edit_file |
Replace an exact string; replace_all: true changes every occurrence at once |
edit_lines |
Replace / insert / delete by line number — add a function, an import, remove a block |
write_file |
Create a file, or replace one whole |
delete_file |
Remove a file or directory |
move_file |
Rename or move |
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.
- 5d ago Changed 11de23566181
- 8d ago First seen · 82 lines · 45 tokens per session scan A 160000ad305e
local-project-context is a skill published in the GitHub repository makifbaysal/tasktrooper (113 stars, last pushed yesterday), licensed Apache-2.0. It adds 45 tokens to every session and 1,323 once invoked, about $0.0002 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 2026-10-05.
Other skills, from other repositories
slack
Use the assigned Slack bot from Slack conversations, Paperclip tasks, and routines to read shared discussions and collaborate.
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
klide
Continue this conversation in the Klide app. Use when the user asks to open, continue, move or hand off this session to Klide — "open this in Klide", "continue in Klide", "send this conv to Klide".
local-document-organizer
Preview-first local file organizer. Scan a user-named folder, classify files with readable rules, show a plan, execute approved moves and undo them. Use for sorting Downloads, renaming into category folders, or reviewing organization history, including scoped metadata-only course persistence. Do not use for knowledge…
customer-email-assist
Review Gmail customer-support threads with a minimal-token, connector-first workflow. Use when Codex needs to read Gmail through the Codex Gmail connector, import cleaned messages into a local SQLite issue queue, apply deterministic cleanup and classification first, reserve model usage for JSON-only message…
personal-workflow-automation
Define, preview, execute and inspect manually triggered workflows with ordered deterministic tool steps and approval gates. Use for repeatable multi-step course routines and explicit retries. Do not use for file classification, knowledge synthesis, background scheduling or replacing another skill's work.