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 danielkinneyspears/govcon-pursuit-brain --skill analyzing-competitorsgit clone --depth 1 https://github.com/danielkinneyspears/govcon-pursuit-brainWrote 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/danielkinneyspears/govcon-pursuit-brain/analyzing-competitors)<a href="https://agentmods.dev/skills/danielkinneyspears/govcon-pursuit-brain/analyzing-competitors"><img src="https://agentmods.dev/badge/skills/danielkinneyspears/govcon-pursuit-brain/analyzing-competitors/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/danielkinneyspears/govcon-pursuit-brain/analyzing-competitors"><img src="https://agentmods.dev/badge/skills/danielkinneyspears/govcon-pursuit-brain/analyzing-competitors.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 | $0.00108 | $0.02236 |
| Opus 5 | $0.00054 | $0.01118 |
| Sonnet 5 | $0.00022 | $0.00447 |
| Haiku 4.5 | $0.00011 | $0.00224 |
Grade A, and why
analyzing-competitors 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 10d 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyzing Competitors
Run a Black Hat competitive assessment and record it as a living subgraph of the pursuit wiki: one entity page per competitor, each modeling how that competitor will bid. The core technique is perspective — bid the job as each competitor would. The wiki payoff is that the assessment does not sit in one flat document: each competitor page links to the customer hot buttons it threatens, the team's exposures it creates, and later the win themes built to counter it.
When to use this skill
Use this skill during capture, once a pursuit wiki exists (created by
qualifying-opportunities), to assess the competitive field. It enriches any
low-confidence competitors/ stubs the bid-decision left behind, and it feeds
price-to-win and win-strategy work.
Architecture
This skill is wiki-native. Read docs/architecture.md
and the conventions first. It reads sources and
entities, maintains competitors/ and risks/ entity pages, and renders
the competitive-assessment.md view. Relevant domain-wiki pages:
[[discriminator]], [[best-value-tradeoff]], [[lpta]].
Inputs
Required: an existing pursuit wiki. Read pursuit.md (note the posture —
it frames the whole assessment), the customer/ entities, the
decisions/bid-decision.md entity, and any competitors/ stubs.
Private company context (recommended). If pursuit.md carries a
company_context_path:, read these company-context folders before intake:
partners/: competitors that are also your partners on other deals, or former partners, or candidate teammates here. The relationship history is load-bearing.debrief-lessons/: what prior debriefs told you about how these competitors actually bid against you.customers/<this-agency>/: your prior interactions with this customer that reveal what the customer thinks of each competitor.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 184 lines · 108 tokens per session scan A 1498d22b120e
analyzing-competitors is a skill published in the GitHub repository danielkinneyspears/govcon-pursuit-brain (5 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 108 tokens to every session and 2,236 once invoked, about $0.0005 per session on Opus 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 2026-08-31.
Other skills, from other repositories
analyzing-competitors
Produces a Black Hat competitive assessment for a US Federal opportunity. Use when the user needs competitive analysis, a Black Hat review or session, competitor profiling, an incumbent assessment, or wants to understand the competitive field for a federal bid. Identifies likely competitors, models each one's probable…
auditing-commitments
Audits a US Federal proposal draft for the obligations it creates, and flags promises stronger than the solicitation requires. Use when the user needs a commitment audit, a promise review, an obligation review, a check for overcommitting, a review of "we will" and "shall" language, a check that the draft does not…
checking-submission-compliance
Runs the final production and submission-compliance check on a US Federal proposal before submission. Use when the user needs a submission compliance check, a final compliance review, a production check, a page-count or format check, a forms and certifications check, or a pre-submission checklist for a federal bid.…
developing-win-strategy
Develops the win strategy for a US Federal proposal. Use when the user needs win themes, discriminators, a win strategy, a value proposition, key messages, proposal themes, or ghosting language for a federal bid. Validates discriminators against a value-and-rarity test, builds substantiated win themes that connect…
estimating-price-to-win
Produces a price-to-win analysis for a US Federal opportunity. Use when the user needs price-to-win, PTW, a competitive pricing analysis, a price target or price range, or wants to understand pricing strategy, cost drivers, and pricing levers for a federal bid. Estimates the competitive price range and a target price…
planning-capture
Builds and maintains a living capture plan for a US Federal opportunity in the pre-RFP capture phase. Use when the user needs a capture plan, capture strategy, customer call plan, customer engagement or shaping plan, or wants to organize pre-RFP positioning work, intelligence gaps, teaming actions, and capture…