{"slug": "your-docs-aren-t-burning-your-tokens-your-tooling-is", "title": "Your docs aren't burning your tokens — your tooling is", "summary": "A developer argues that documentation in the Product Development Life Cycle (PDLC) does not significantly increase token usage; instead, inefficient tooling and rework are the primary token drains. The developer emphasizes that docs are assets that reduce rework and save tokens long-term, and advises optimizing tool usage rather than cutting documentation.", "body_md": "📝 Originally on my blog →\n\n[https://kanfu-panda.github.io/blog/2026/06/16/tokens-not-docs.html]\n\nPeople keep asking me the same thing about running projects with PDLC: with all those docs — PRD, design, review at every step — aren't you burning tokens like crazy?\n\nIt's a fair question. The process is broken into fine-grained stages, each leaving an artifact behind, and that does look more expensive than just \"letting the AI write the code.\" But I'd argue you can't put the token bill on the docs.\n\nLet me put the conclusion up front. First: having lots of docs and burning lots of tokens are two different things. Second: even if you genuinely want to cut tokens, the answer is using your tools correctly, not cutting the docs.\n\nI haven't measured tokens precisely — I didn't run the same project twice, with and without docs, to get a clean percentage. What I have is hands-on experience and methods.\n\nBefore you settle the bill, find the right debtor.\n\nMost of the time, burning tokens isn't caused by PDLC — it's tooling used wrong. And \"wrong\" is concrete, in three places:\n\nAnd the most common one: never turning on the token-saving methods at all, then blaming the process for being heavy.\n\nYou can't charge any of this to \"PDLC has too many docs.\" Docs sit quietly in `docs/`\n\nand never burn a single token on their own. What burns tokens is the usage above.\n\nIn my own experience, the biggest token sink has never been generating docs — it's rework.\n\nRewriting because the direction was wrong, tearing things down because the requirement was misread, going back because fixing one thing broke another — every one of those round-trips is real tokens. Generating a PRD is a one-time cost; rework from a wrong direction compounds.\n\nThis heavy-looking PDLC process is precisely trading \"write a bit more up front\" for \"rework a lot less later.\" Once you are using it, the whole flow is steadier and so is the final output — no back-and-forth. Less rework is, in itself, fewer tokens burned.\n\nSo here is how I see it: docs aren't a cost, they're an asset. They leave a trace of the design decisions and the why, so you can trace back and audit. Next time the AI picks it up, it reads the docs and gets it — I don't re-explain from scratch. That saved stretch is, again, tokens.\n\nSaving tokens isn't about not writing docs — it's saving where saving belongs. The ones I actually use on my machine, roughly:\n\n`git status`\n\n, squeeze the output; it adds up.Not one of these is \"write fewer docs.\"\n\nThat said, PDLC doesn't mean running the full suite on every change.\n\nA one-line bug fix — do you need a PRD, a design review? Depends; most of the time there's no need for the heavy process, so trim it. The criterion is simple: is this change worth leaving an asset for? If yes, run the full thing; for one-off small fixes, nobody blames you for cutting a few steps.\n\nAnd \"saving tokens = saving money\" needs to be said per billing model, or it misleads:\n\nI use both. Figure out which one you're on first; that's what tells you what \"saving tokens\" actually means for you.\n\nTo sum up: lots of docs doesn't equal burning tokens; if you really want to save, save on how you use your tools, not on the docs.\n\nThe one thing I most want to say: docs are an asset, not a cost. Trying to save tokens by \"not writing docs, just letting the AI emit code\" looks like savings short-term, but the project won't go far — no trace, no traceability, and two months later you can't even say why you designed it this way. The rework then burns far more than the doc tokens you saved.\n\nOne thing you can do today: look back at whether you've turned on the token-saving methods — is your context trimmed? Are you still sending everything to the strongest model instead of tiering? Did you cut the costs you could? And while you're at it, ask whether you're using PDLC well too.\n\nThere's a lot more to unpack on saving tokens — how exactly to tier models, when to clear context, how to actually land the caching discount. I'll pick one and go deeper next time.", "url": "https://wpnews.pro/news/your-docs-aren-t-burning-your-tokens-your-tooling-is", "canonical_source": "https://dev.to/kanfu-panda/your-docs-arent-burning-your-tokens-your-tooling-is-58ck", "published_at": "2026-06-20 08:43:28+00:00", "updated_at": "2026-06-20 09:07:08.881546+00:00", "lang": "en", "topics": ["large-language-models", "developer-tools", "ai-products"], "entities": ["PDLC", "PRD", "AI"], "alternates": {"html": "https://wpnews.pro/news/your-docs-aren-t-burning-your-tokens-your-tooling-is", "markdown": "https://wpnews.pro/news/your-docs-aren-t-burning-your-tokens-your-tooling-is.md", "text": "https://wpnews.pro/news/your-docs-aren-t-burning-your-tokens-your-tooling-is.txt", "jsonld": "https://wpnews.pro/news/your-docs-aren-t-burning-your-tokens-your-tooling-is.jsonld"}}