1# nasin pali (the way of work)
2
3[](https://api.reuse.software/info/git.secluded.site/nasin-pali)
4[](https://goreportcard.com/report/git.secluded.site/nasin-pali)
5
6**This README is aspirational!** None of the code exists yet, I'm just getting
7my ideas down. I previously wrote a
8[planning-mcp-server](https://git.secluded.site/planning-mcp-server) that I'll
9keep some ideas from, and the overall workflow is about the same. I'm trying a
10CLI over MCP because MCP seems quite protocol-heavy for what _could_ just be a
11few simple CLI invocations. Maybe connecting arbitrarty data sources warrants a
12whole protocol like MCP, but I don't think something as basic as this does. Just
13some thoughtful design and prompting.
14
15---
16
17## Overview
18
19_nasin pali_, installed as `np`, is a CLI tool that encourages LLMs in agentic
20coding tools (specifically coding, I don't think we want to support generic
21workflows) to do a bit more planning before going off and making a bunch of
22changes. It is _both_ meant for humans and LLMs; there are subcommands that
23produce output for the model and subcommands for the human to inspect the
24model's progress. There's a section on [the name](#the-name) if you're curious
25about it.
26
27The todo systems built into agentic coding tools are often just that: todo and
28nothing else. I think (backed by no evidence) that they do better when they can
29also set a goal. If I understand the coding tools correctly, they also have the
30LLM reproduce the entire task list with each `todo_write` invocation, which just
31seems wasteful and careless to me. What if it decides it doesn't want to do a
32task because it's "too hard" and it just omits that task next time it writes the
33list? _nasin pali_ helps force the model into a different overall flow.
34
35## Expected workflow
36
37_This is what I like, I'd be happy to hear of other workflows that lead to
38better/different success and to consider whether nasin-pali can support them_
39
40The operator is expected to load the prompt up with relevant text. Type the
41issue in the prompt, paste the bug report, tell it how to fetch the issue from
42your issue tracker, whatever you like. If the issue content is too sparse, make
43sure to add more context. The more context you give and the higher its quality
44and relevancy, the better results you'll have. Include paths to as many files
45you know will be relevant as possible. Mention particular symbols, paste
46snippets of code, etc. Once your prompt looks good, send it off.
47
48In the `np` section of the model's rules, we'll have instructions to
49_immediately_ set an overarching goal with `np g s -t title -d description` that
50captures the operator's request, combining the information from the ticket and
51any extra operator-provided context. It should then go off and look at the
52provided references and thoroughly consider how to go about resolving the goal.
53After gathering that context, it adds tasks with `np t a -t title -d description
54-t title2 -d description2` and gets started on them.
55
56I'm unsure how to handle session archival (mentioned in [random
57thoughts](#random-thoughts)). We could tell the model how to archive sessions in
58the rules, but I don't know that the model even needs to know about sessions;
59maybe archival should require human interaction. If the model can't archive
60sessions, and the agentic coding tool doesn't have a way for the operator to
61execute shell commands, they'd have to quit or open a new shell to run that
62command before the model can create a new one session. Maybe telling it about
63the archival command, but to never run it without operator interaction, would be
64sufficient.
65
66## The name
67
68Is [toki pona](https://tokipona.org/). [_nasin_](https://nimi.li/nasin) occupies
69the semantic space of "method, doctrine, tradition; path, road, way" while
70[_pali_](https://nimi.li/pali) covers "work, activity; create, build, design;
71put effort toward, take action on". Together and in this context, _nasin pali_
72could be translated as "the way of work", "the doctrine of design", etc.
73
74## Random thoughts
75
76- When providing multiple lines for the body, use
77
78 ```bash
79 np goal set "Sentence case title" "$(cat <<'EOF'
80 Multi-line
81 - Body
82 - Here
83
84 EOF
85 )"
86 ```
87
88- I like the way
89 [planning-mcp-server](https://git.secluded.site/planning-mcp-server#tracking-progress)
90 renders the task list in unicode characters. `☑` is one token while `- [x]` is
91 probably like five.
92- Start a new session with `np s`. It adds details to the global sqlite database
93 and produces output to guide the LLM through its next steps. Instead of
94 telling the model up-front about everything it can do with _nasin pali_ though
95 AGENTS.md or tool definitions or something, we only reveal the sub-commands
96 and flags it might actually need once it needs them. It shouldn't ever use the
97 interactive commands, so we never tell them model about them.
98 - There can be one active session per working directory and the previous
99 session must be archived before starting a new one. This is so the model
100 doesn't have to provide a session ID or something for each invocation.
101- `np s` tells the model about the goal and task sub-commands and their flags
102 and to begin the session by turning the user's request, bug report, issue
103 contents, spec, etc. into a concise overarching goal with a thorough
104 description.
105- `np g s` accepts title and description arguments and tells the model to, if
106 necessary, look around at additional relevant files before adding some tasks
107 with `np t a`. <mark>How to provide/require/validate for pairs of -t and -d
108 flags?</mark>
109- Have the model update task statuses by ID and render the goal, the updated
110 task, and the _remaining_ tasks in the same format as planning-mcp-server. By
111 default, `planning-mcp-server` returned all tasks, but I think it would be
112 better to just return the modified one, so the model can see its previous
113 command worked, and the still-open ones. Include a flag or something so it can
114 look at all tasks including the completed ones.